Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6360 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1672. Min Range: -10.1672
Max Act: 10.1672. Min Act: -0.1700
Data Index: 4087787 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1672. Min Range: -10.1672
Max Act: 9.9172. Min Act: -0.1700
Data Index: 4678114 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1672. Min Range: -10.1672
Max Act: 9.6672. Min Act: -0.1700
Data Index: 114726 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1672. Min Range: -10.1672
Max Act: 9.3547. Min Act: -0.1700
Data Index: 6633405 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1672. Min Range: -10.1672
Max Act: 9.2922. Min Act: -0.1700
Data Index: 6754968 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1672. Min Range: -10.1672
Max Act: 9.1672. Min Act: -0.1700
Data Index: 4569406 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1672. Min Range: -10.1672
Max Act: 9.1672. Min Act: -0.1700
Data Index: 6980482 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1672. Min Range: -10.1672
Max Act: 8.9797. Min Act: -0.1700
Data Index: 4170064 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1672. Min Range: -10.1672
Max Act: 8.8547. Min Act: -0.1700
Data Index: 633380 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1672. Min Range: -10.1672
Max Act: 8.7922. Min Act: -0.1700
Data Index: 6475325 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1672. Min Range: -10.1672
Max Act: 8.7922. Min Act: -0.1700
Data Index: 5466232 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1672. Min Range: -10.1672
Max Act: 8.7297. Min Act: -0.1700
Data Index: 1341275 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1672. Min Range: -10.1672
Max Act: 8.7297. Min Act: -0.1700
Data Index: 3108799 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1672. Min Range: -10.1672
Max Act: 8.7297. Min Act: -0.1700
Data Index: 5166998 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1672. Min Range: -10.1672
Max Act: 8.6047. Min Act: -0.1700
Data Index: 4731983 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1672. Min Range: -10.1672
Max Act: 8.7297. Min Act: -0.1700
Data Index: 98843 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1672. Min Range: -10.1672
Max Act: 8.6672. Min Act: -0.1700
Data Index: 2982870 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1672. Min Range: -10.1672
Max Act: 8.6047. Min Act: -0.1700
Data Index: 192291 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1672. Min Range: -10.1672
Max Act: 8.6047. Min Act: -0.1700
Data Index: 1973898 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1672. Min Range: -10.1672
Max Act: 8.6047. Min Act: -0.1700
Data Index: 3611231 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19