Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3486 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.7326. Min Act: -0.1700
Data Index: 4853669 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.7326. Min Act: -0.1700
Data Index: 14165 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.7326. Min Act: -0.1700
Data Index: 2409858 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.6389. Min Act: -0.1700
Data Index: 321353 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.6389. Min Act: -0.1700
Data Index: 4234840 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.6389. Min Act: -0.1700
Data Index: 7828574 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.5764. Min Act: -0.1700
Data Index: 4371314 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.5764. Min Act: -0.1700
Data Index: 8319398 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.5139. Min Act: -0.1700
Data Index: 7919546 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.4826. Min Act: -0.1700
Data Index: 8810410 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.4826. Min Act: -0.1700
Data Index: 8616538 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.4826. Min Act: -0.1700
Data Index: 5286186 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.4826. Min Act: -0.1700
Data Index: 2435102 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.4201. Min Act: -0.1700
Data Index: 3795051 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.4514. Min Act: -0.1700
Data Index: 2474023 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.4514. Min Act: -0.1700
Data Index: 5813290 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.4826. Min Act: -0.1700
Data Index: 4853670 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.4514. Min Act: -0.1700
Data Index: 1620339 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.4201. Min Act: -0.1700
Data Index: 5042000 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.4201. Min Act: -0.1700
Data Index: 3422369 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19