Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0286. Min Range: -3.0286
Max Act: 3.0286. Min Act: -0.1700
Data Index: 4462799 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0286. Min Range: -3.0286
Max Act: 2.9654. Min Act: -0.1700
Data Index: 876926 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0286. Min Range: -3.0286
Max Act: 2.9495. Min Act: -0.1700
Data Index: 4375868 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0286. Min Range: -3.0286
Max Act: 2.9495. Min Act: -0.1700
Data Index: 5137082 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0286. Min Range: -3.0286
Max Act: 2.9179. Min Act: -0.1700
Data Index: 7996152 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0286. Min Range: -3.0286
Max Act: 2.9020. Min Act: -0.1700
Data Index: 2876992 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0286. Min Range: -3.0286
Max Act: 2.9179. Min Act: -0.1700
Data Index: 3908129 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0286. Min Range: -3.0286
Max Act: 2.9020. Min Act: -0.1700
Data Index: 7815320 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0286. Min Range: -3.0286
Max Act: 2.8861. Min Act: -0.1700
Data Index: 8611388 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0286. Min Range: -3.0286
Max Act: 2.8861. Min Act: -0.1700
Data Index: 1574973 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0286. Min Range: -3.0286
Max Act: 2.9020. Min Act: -0.1700
Data Index: 3413650 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0286. Min Range: -3.0286
Max Act: 2.9020. Min Act: -0.1700
Data Index: 2874088 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0286. Min Range: -3.0286
Max Act: 2.9179. Min Act: -0.1700
Data Index: 836163 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0286. Min Range: -3.0286
Max Act: 2.9020. Min Act: -0.1700
Data Index: 4530173 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0286. Min Range: -3.0286
Max Act: 2.8861. Min Act: -0.1700
Data Index: 3026256 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0286. Min Range: -3.0286
Max Act: 2.8703. Min Act: -0.1700
Data Index: 7360789 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0286. Min Range: -3.0286
Max Act: 2.8703. Min Act: -0.1700
Data Index: 4485322 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0286. Min Range: -3.0286
Max Act: 2.8703. Min Act: -0.1700
Data Index: 6519537 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0286. Min Range: -3.0286
Max Act: 2.8703. Min Act: -0.1700
Data Index: 2332457 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0286. Min Range: -3.0286
Max Act: 2.8544. Min Act: -0.1700
Data Index: 7640439 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19