Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4558 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.6701. Min Act: -0.1700
Data Index: 518884 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.6701. Min Act: -0.1700
Data Index: 8326666 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.5451. Min Act: -0.1700
Data Index: 6536263 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.5139. Min Act: -0.1700
Data Index: 778523 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.4514. Min Act: -0.1700
Data Index: 5543787 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.4514. Min Act: -0.1700
Data Index: 8326665 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.4514. Min Act: -0.1700
Data Index: 131840 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.4514. Min Act: -0.1700
Data Index: 590695 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.4514. Min Act: -0.1700
Data Index: 4249192 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.3889. Min Act: -0.1700
Data Index: 4643386 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.3889. Min Act: -0.1700
Data Index: 6574260 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.3889. Min Act: -0.1700
Data Index: 8534007 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.4201. Min Act: -0.1700
Data Index: 3577130 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.3576. Min Act: -0.1700
Data Index: 1821015 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.3576. Min Act: -0.1700
Data Index: 5451026 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.3576. Min Act: -0.1700
Data Index: 6287971 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.3576. Min Act: -0.1700
Data Index: 6675885 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.3576. Min Act: -0.1700
Data Index: 5955461 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.3264. Min Act: -0.1700
Data Index: 8094815 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6701. Min Range: -4.6701
Max Act: 4.3264. Min Act: -0.1700
Data Index: 5138389 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19