Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1207 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 12.0299. Min Range: -12.0299
Max Act: 12.0299. Min Act: -0.1700
Data Index: 5550839 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0299. Min Range: -12.0299
Max Act: 12.0299. Min Act: -0.1700
Data Index: 1439825 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0299. Min Range: -12.0299
Max Act: 11.8424. Min Act: -0.1700
Data Index: 7343711 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0299. Min Range: -12.0299
Max Act: 11.7799. Min Act: -0.1700
Data Index: 8335419 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0299. Min Range: -12.0299
Max Act: 11.7174. Min Act: -0.1700
Data Index: 1649502 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0299. Min Range: -12.0299
Max Act: 11.5299. Min Act: -0.1700
Data Index: 5219739 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0299. Min Range: -12.0299
Max Act: 11.5924. Min Act: -0.1700
Data Index: 7692845 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0299. Min Range: -12.0299
Max Act: 11.4674. Min Act: -0.1700
Data Index: 6543075 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0299. Min Range: -12.0299
Max Act: 11.4674. Min Act: -0.1700
Data Index: 5291093 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0299. Min Range: -12.0299
Max Act: 11.4049. Min Act: -0.1700
Data Index: 1615105 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0299. Min Range: -12.0299
Max Act: 11.3424. Min Act: -0.1700
Data Index: 1071327 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0299. Min Range: -12.0299
Max Act: 11.3424. Min Act: -0.1700
Data Index: 8038279 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0299. Min Range: -12.0299
Max Act: 11.4674. Min Act: -0.1700
Data Index: 2379515 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0299. Min Range: -12.0299
Max Act: 11.3424. Min Act: -0.1700
Data Index: 3258622 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0299. Min Range: -12.0299
Max Act: 11.3424. Min Act: -0.1700
Data Index: 2045138 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0299. Min Range: -12.0299
Max Act: 11.3424. Min Act: -0.1700
Data Index: 7648482 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0299. Min Range: -12.0299
Max Act: 11.2799. Min Act: -0.1700
Data Index: 4756859 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0299. Min Range: -12.0299
Max Act: 11.2799. Min Act: -0.1700
Data Index: 3063704 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0299. Min Range: -12.0299
Max Act: 11.2174. Min Act: -0.1700
Data Index: 792182 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0299. Min Range: -12.0299
Max Act: 11.2174. Min Act: -0.1700
Data Index: 611372 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19