Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1935 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 8.4290. Min Range: -8.4290
Max Act: 8.3665. Min Act: -0.1700
Data Index: 1466942 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4290. Min Range: -8.4290
Max Act: 8.4290. Min Act: -0.1700
Data Index: 1466941 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4290. Min Range: -8.4290
Max Act: 8.3665. Min Act: -0.1700
Data Index: 5868382 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4290. Min Range: -8.4290
Max Act: 8.3040. Min Act: -0.1700
Data Index: 4988695 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4290. Min Range: -8.4290
Max Act: 8.2415. Min Act: -0.1700
Data Index: 5731441 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4290. Min Range: -8.4290
Max Act: 8.3040. Min Act: -0.1700
Data Index: 4677673 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4290. Min Range: -8.4290
Max Act: 8.2415. Min Act: -0.1700
Data Index: 6300803 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4290. Min Range: -8.4290
Max Act: 8.2415. Min Act: -0.1700
Data Index: 3978033 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4290. Min Range: -8.4290
Max Act: 8.1790. Min Act: -0.1700
Data Index: 1551910 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4290. Min Range: -8.4290
Max Act: 8.0540. Min Act: -0.1700
Data Index: 4216415 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4290. Min Range: -8.4290
Max Act: 8.1165. Min Act: -0.1700
Data Index: 4954737 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4290. Min Range: -8.4290
Max Act: 8.1165. Min Act: -0.1700
Data Index: 3193908 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4290. Min Range: -8.4290
Max Act: 8.1165. Min Act: -0.1700
Data Index: 2497524 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4290. Min Range: -8.4290
Max Act: 8.0540. Min Act: -0.1700
Data Index: 4310813 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4290. Min Range: -8.4290
Max Act: 8.1165. Min Act: -0.1700
Data Index: 8366368 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4290. Min Range: -8.4290
Max Act: 8.0540. Min Act: -0.1700
Data Index: 567826 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4290. Min Range: -8.4290
Max Act: 8.0540. Min Act: -0.1700
Data Index: 2849112 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4290. Min Range: -8.4290
Max Act: 7.9915. Min Act: -0.1700
Data Index: 4997433 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4290. Min Range: -8.4290
Max Act: 8.0540. Min Act: -0.1700
Data Index: 5652546 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4290. Min Range: -8.4290
Max Act: 8.0540. Min Act: -0.1700
Data Index: 6323073 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19