Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3664 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0193. Min Range: -5.0193
Max Act: 5.0193. Min Act: -0.1700
Data Index: 7484477 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0193. Min Range: -5.0193
Max Act: 4.8630. Min Act: -0.1700
Data Index: 4093114 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0193. Min Range: -5.0193
Max Act: 4.8630. Min Act: -0.1700
Data Index: 6126685 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0193. Min Range: -5.0193
Max Act: 4.8318. Min Act: -0.1700
Data Index: 7311730 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0193. Min Range: -5.0193
Max Act: 4.7380. Min Act: -0.1700
Data Index: 670250 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0193. Min Range: -5.0193
Max Act: 4.7693. Min Act: -0.1700
Data Index: 6789759 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0193. Min Range: -5.0193
Max Act: 4.6443. Min Act: -0.1700
Data Index: 3253937 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0193. Min Range: -5.0193
Max Act: 4.6443. Min Act: -0.1700
Data Index: 1574022 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0193. Min Range: -5.0193
Max Act: 4.6130. Min Act: -0.1700
Data Index: 8670649 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0193. Min Range: -5.0193
Max Act: 4.6130. Min Act: -0.1700
Data Index: 1756797 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0193. Min Range: -5.0193
Max Act: 4.6130. Min Act: -0.1700
Data Index: 4553580 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0193. Min Range: -5.0193
Max Act: 4.6130. Min Act: -0.1700
Data Index: 356966 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0193. Min Range: -5.0193
Max Act: 4.5818. Min Act: -0.1700
Data Index: 39188 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0193. Min Range: -5.0193
Max Act: 4.5818. Min Act: -0.1700
Data Index: 1264529 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0193. Min Range: -5.0193
Max Act: 4.5818. Min Act: -0.1700
Data Index: 2212375 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0193. Min Range: -5.0193
Max Act: 4.5818. Min Act: -0.1700
Data Index: 3969993 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0193. Min Range: -5.0193
Max Act: 4.5818. Min Act: -0.1700
Data Index: 1577418 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0193. Min Range: -5.0193
Max Act: 4.5818. Min Act: -0.1700
Data Index: 8157119 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0193. Min Range: -5.0193
Max Act: 4.5505. Min Act: -0.1700
Data Index: 3027747 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0193. Min Range: -5.0193
Max Act: 4.5505. Min Act: -0.1700
Data Index: 4802892 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19