Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 270 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3366. Min Range: -5.3366
Max Act: 5.3366. Min Act: -0.1700
Data Index: 1699271 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3366. Min Range: -5.3366
Max Act: 5.2741. Min Act: -0.1700
Data Index: 6406241 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3366. Min Range: -5.3366
Max Act: 5.2116. Min Act: -0.1700
Data Index: 6665474 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3366. Min Range: -5.3366
Max Act: 4.9616. Min Act: -0.1700
Data Index: 7797841 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3366. Min Range: -5.3366
Max Act: 4.9929. Min Act: -0.1700
Data Index: 4091009 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3366. Min Range: -5.3366
Max Act: 4.9304. Min Act: -0.1700
Data Index: 1351050 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3366. Min Range: -5.3366
Max Act: 4.9304. Min Act: -0.1700
Data Index: 6103587 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3366. Min Range: -5.3366
Max Act: 4.8991. Min Act: -0.1700
Data Index: 3487248 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3366. Min Range: -5.3366
Max Act: 4.8679. Min Act: -0.1700
Data Index: 6117205 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3366. Min Range: -5.3366
Max Act: 4.8366. Min Act: -0.1700
Data Index: 6856081 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3366. Min Range: -5.3366
Max Act: 4.8679. Min Act: -0.1700
Data Index: 699494 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3366. Min Range: -5.3366
Max Act: 4.8366. Min Act: -0.1700
Data Index: 455944 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3366. Min Range: -5.3366
Max Act: 4.8366. Min Act: -0.1700
Data Index: 6103586 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3366. Min Range: -5.3366
Max Act: 4.8366. Min Act: -0.1700
Data Index: 5555845 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3366. Min Range: -5.3366
Max Act: 4.8366. Min Act: -0.1700
Data Index: 934982 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3366. Min Range: -5.3366
Max Act: 4.8054. Min Act: -0.1700
Data Index: 4905591 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3366. Min Range: -5.3366
Max Act: 4.7741. Min Act: -0.1700
Data Index: 6003578 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3366. Min Range: -5.3366
Max Act: 4.7429. Min Act: -0.1700
Data Index: 89588 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3366. Min Range: -5.3366
Max Act: 4.7429. Min Act: -0.1700
Data Index: 725760 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3366. Min Range: -5.3366
Max Act: 4.7116. Min Act: -0.1700
Data Index: 5555841 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19