Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4020 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1442. Min Range: -5.1442
Max Act: 5.1442. Min Act: -0.1700
Data Index: 4728192 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1442. Min Range: -5.1442
Max Act: 5.0505. Min Act: -0.1700
Data Index: 7418108 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1442. Min Range: -5.1442
Max Act: 5.0192. Min Act: -0.1700
Data Index: 3072861 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1442. Min Range: -5.1442
Max Act: 5.0192. Min Act: -0.1700
Data Index: 5750540 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1442. Min Range: -5.1442
Max Act: 4.9880. Min Act: -0.1700
Data Index: 1824791 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1442. Min Range: -5.1442
Max Act: 4.9880. Min Act: -0.1700
Data Index: 5104696 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1442. Min Range: -5.1442
Max Act: 4.9567. Min Act: -0.1700
Data Index: 7430984 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1442. Min Range: -5.1442
Max Act: 4.9567. Min Act: -0.1700
Data Index: 2927512 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1442. Min Range: -5.1442
Max Act: 4.9567. Min Act: -0.1700
Data Index: 1316574 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1442. Min Range: -5.1442
Max Act: 4.9567. Min Act: -0.1700
Data Index: 6605576 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1442. Min Range: -5.1442
Max Act: 4.9567. Min Act: -0.1700
Data Index: 6902378 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1442. Min Range: -5.1442
Max Act: 4.9255. Min Act: -0.1700
Data Index: 3671583 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1442. Min Range: -5.1442
Max Act: 4.9255. Min Act: -0.1700
Data Index: 3531492 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1442. Min Range: -5.1442
Max Act: 4.9255. Min Act: -0.1700
Data Index: 6337191 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1442. Min Range: -5.1442
Max Act: 4.9255. Min Act: -0.1700
Data Index: 3494871 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1442. Min Range: -5.1442
Max Act: 4.8942. Min Act: -0.1700
Data Index: 2211425 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1442. Min Range: -5.1442
Max Act: 4.8942. Min Act: -0.1700
Data Index: 724955 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1442. Min Range: -5.1442
Max Act: 4.8630. Min Act: -0.1700
Data Index: 627146 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1442. Min Range: -5.1442
Max Act: 4.8630. Min Act: -0.1700
Data Index: 503387 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1442. Min Range: -5.1442
Max Act: 4.8630. Min Act: -0.1700
Data Index: 1196653 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19