Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4605 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2432. Min Range: -6.2432
Max Act: 6.2432. Min Act: -0.1700
Data Index: 1646860 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2432. Min Range: -6.2432
Max Act: 6.1182. Min Act: -0.1700
Data Index: 3812314 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2432. Min Range: -6.2432
Max Act: 6.0244. Min Act: -0.1700
Data Index: 329689 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2432. Min Range: -6.2432
Max Act: 6.0244. Min Act: -0.1700
Data Index: 6658579 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2432. Min Range: -6.2432
Max Act: 6.0557. Min Act: -0.1700
Data Index: 5866342 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2432. Min Range: -6.2432
Max Act: 5.9619. Min Act: -0.1700
Data Index: 2262166 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2432. Min Range: -6.2432
Max Act: 5.9619. Min Act: -0.1700
Data Index: 6628673 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2432. Min Range: -6.2432
Max Act: 5.9619. Min Act: -0.1700
Data Index: 8025230 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2432. Min Range: -6.2432
Max Act: 5.9307. Min Act: -0.1700
Data Index: 6708066 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2432. Min Range: -6.2432
Max Act: 5.9619. Min Act: -0.1700
Data Index: 8517363 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2432. Min Range: -6.2432
Max Act: 5.8994. Min Act: -0.1700
Data Index: 866502 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2432. Min Range: -6.2432
Max Act: 5.8994. Min Act: -0.1700
Data Index: 4518308 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2432. Min Range: -6.2432
Max Act: 5.8682. Min Act: -0.1700
Data Index: 6756821 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2432. Min Range: -6.2432
Max Act: 5.8369. Min Act: -0.1700
Data Index: 7159792 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2432. Min Range: -6.2432
Max Act: 5.8369. Min Act: -0.1700
Data Index: 4298377 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2432. Min Range: -6.2432
Max Act: 5.7744. Min Act: -0.1700
Data Index: 8786685 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2432. Min Range: -6.2432
Max Act: 5.7744. Min Act: -0.1700
Data Index: 1060415 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2432. Min Range: -6.2432
Max Act: 5.7432. Min Act: -0.1700
Data Index: 5290249 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2432. Min Range: -6.2432
Max Act: 5.7119. Min Act: -0.1700
Data Index: 3397656 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2432. Min Range: -6.2432
Max Act: 5.7432. Min Act: -0.1700
Data Index: 3667904 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19