Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 433 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3114. Min Range: -4.3114
Max Act: 4.3114. Min Act: -0.1700
Data Index: 3924824 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3114. Min Range: -4.3114
Max Act: 4.1864. Min Act: -0.1700
Data Index: 5971385 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3114. Min Range: -4.3114
Max Act: 4.1239. Min Act: -0.1700
Data Index: 7761350 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3114. Min Range: -4.3114
Max Act: 4.1239. Min Act: -0.1700
Data Index: 3663679 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3114. Min Range: -4.3114
Max Act: 4.0927. Min Act: -0.1700
Data Index: 5008005 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3114. Min Range: -4.3114
Max Act: 4.0927. Min Act: -0.1700
Data Index: 6270677 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3114. Min Range: -4.3114
Max Act: 4.0927. Min Act: -0.1700
Data Index: 1986578 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3114. Min Range: -4.3114
Max Act: 4.0614. Min Act: -0.1700
Data Index: 6240993 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3114. Min Range: -4.3114
Max Act: 4.0614. Min Act: -0.1700
Data Index: 7531373 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3114. Min Range: -4.3114
Max Act: 4.0927. Min Act: -0.1700
Data Index: 5372846 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3114. Min Range: -4.3114
Max Act: 4.0301. Min Act: -0.1700
Data Index: 3393603 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3114. Min Range: -4.3114
Max Act: 4.0301. Min Act: -0.1700
Data Index: 3286810 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3114. Min Range: -4.3114
Max Act: 3.9989. Min Act: -0.1700
Data Index: 3025051 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3114. Min Range: -4.3114
Max Act: 3.9989. Min Act: -0.1700
Data Index: 5399544 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3114. Min Range: -4.3114
Max Act: 3.9989. Min Act: -0.1700
Data Index: 1202584 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3114. Min Range: -4.3114
Max Act: 3.9989. Min Act: -0.1700
Data Index: 4095484 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3114. Min Range: -4.3114
Max Act: 3.9989. Min Act: -0.1700
Data Index: 7039448 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3114. Min Range: -4.3114
Max Act: 3.9989. Min Act: -0.1700
Data Index: 1290821 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3114. Min Range: -4.3114
Max Act: 3.9989. Min Act: -0.1700
Data Index: 2100736 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3114. Min Range: -4.3114
Max Act: 3.9676. Min Act: -0.1700
Data Index: 730067 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19