Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4842 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1397. Min Range: -8.1397
Max Act: 8.1397. Min Act: -0.1700
Data Index: 4431153 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1397. Min Range: -8.1397
Max Act: 8.0147. Min Act: -0.1700
Data Index: 6373976 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1397. Min Range: -8.1397
Max Act: 7.8272. Min Act: -0.1700
Data Index: 5307522 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1397. Min Range: -8.1397
Max Act: 7.7647. Min Act: -0.1700
Data Index: 6539587 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1397. Min Range: -8.1397
Max Act: 7.7647. Min Act: -0.1700
Data Index: 1802364 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1397. Min Range: -8.1397
Max Act: 7.7647. Min Act: -0.1700
Data Index: 2292509 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1397. Min Range: -8.1397
Max Act: 7.7022. Min Act: -0.1700
Data Index: 322448 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1397. Min Range: -8.1397
Max Act: 7.7022. Min Act: -0.1700
Data Index: 3137144 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1397. Min Range: -8.1397
Max Act: 7.7022. Min Act: -0.1700
Data Index: 101173 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1397. Min Range: -8.1397
Max Act: 7.7022. Min Act: -0.1700
Data Index: 2986562 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1397. Min Range: -8.1397
Max Act: 7.7022. Min Act: -0.1700
Data Index: 4931678 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1397. Min Range: -8.1397
Max Act: 7.7022. Min Act: -0.1700
Data Index: 8651523 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1397. Min Range: -8.1397
Max Act: 7.7022. Min Act: -0.1700
Data Index: 6771449 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1397. Min Range: -8.1397
Max Act: 7.7022. Min Act: -0.1700
Data Index: 495148 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1397. Min Range: -8.1397
Max Act: 7.7022. Min Act: -0.1700
Data Index: 7989274 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1397. Min Range: -8.1397
Max Act: 7.7022. Min Act: -0.1700
Data Index: 6511691 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1397. Min Range: -8.1397
Max Act: 7.6397. Min Act: -0.1700
Data Index: 4943740 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1397. Min Range: -8.1397
Max Act: 7.6397. Min Act: -0.1700
Data Index: 108507 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1397. Min Range: -8.1397
Max Act: 7.6397. Min Act: -0.1700
Data Index: 6611217 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1397. Min Range: -8.1397
Max Act: 7.6084. Min Act: -0.1700
Data Index: 7622065 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19