Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 138 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.7541. Min Act: -0.1700
Data Index: 8256712 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.7228. Min Act: -0.1700
Data Index: 2913551 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.6916. Min Act: -0.1700
Data Index: 535484 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.6916. Min Act: -0.1700
Data Index: 2913552 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.6916. Min Act: -0.1700
Data Index: 4509162 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.6603. Min Act: -0.1700
Data Index: 3378322 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.6291. Min Act: -0.1700
Data Index: 3209672 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.5666. Min Act: -0.1700
Data Index: 2169142 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.5666. Min Act: -0.1700
Data Index: 273479 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.5666. Min Act: -0.1700
Data Index: 386887 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.5353. Min Act: -0.1700
Data Index: 6796120 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.5041. Min Act: -0.1700
Data Index: 1264648 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.5041. Min Act: -0.1700
Data Index: 7742613 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.5041. Min Act: -0.1700
Data Index: 6568429 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.5041. Min Act: -0.1700
Data Index: 273481 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.5041. Min Act: -0.1700
Data Index: 2639701 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.5041. Min Act: -0.1700
Data Index: 287277 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.5041. Min Act: -0.1700
Data Index: 5709209 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.5041. Min Act: -0.1700
Data Index: 8617648 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7541. Min Range: -5.7541
Max Act: 5.5041. Min Act: -0.1700
Data Index: 1156912 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19