Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4280 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.0323. Min Range: -13.0323
Max Act: 13.0323. Min Act: -0.1700
Data Index: 974833 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.0323. Min Range: -13.0323
Max Act: 12.5948. Min Act: -0.1700
Data Index: 7093110 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.0323. Min Range: -13.0323
Max Act: 12.4073. Min Act: -0.1700
Data Index: 4557604 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.0323. Min Range: -13.0323
Max Act: 12.3448. Min Act: -0.1700
Data Index: 6415131 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.0323. Min Range: -13.0323
Max Act: 12.2823. Min Act: -0.1700
Data Index: 1042771 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.0323. Min Range: -13.0323
Max Act: 12.1573. Min Act: -0.1700
Data Index: 5125875 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.0323. Min Range: -13.0323
Max Act: 12.1573. Min Act: -0.1700
Data Index: 3953089 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.0323. Min Range: -13.0323
Max Act: 12.1573. Min Act: -0.1700
Data Index: 6085729 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.0323. Min Range: -13.0323
Max Act: 12.0948. Min Act: -0.1700
Data Index: 21138 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.0323. Min Range: -13.0323
Max Act: 12.1573. Min Act: -0.1700
Data Index: 4637413 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.0323. Min Range: -13.0323
Max Act: 12.0323. Min Act: -0.1700
Data Index: 5672674 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.0323. Min Range: -13.0323
Max Act: 11.9698. Min Act: -0.1700
Data Index: 4826759 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.0323. Min Range: -13.0323
Max Act: 11.9698. Min Act: -0.1700
Data Index: 5819765 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.0323. Min Range: -13.0323
Max Act: 11.9698. Min Act: -0.1700
Data Index: 542580 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.0323. Min Range: -13.0323
Max Act: 11.9073. Min Act: -0.1700
Data Index: 3183499 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.0323. Min Range: -13.0323
Max Act: 11.9698. Min Act: -0.1700
Data Index: 1811399 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.0323. Min Range: -13.0323
Max Act: 11.9698. Min Act: -0.1700
Data Index: 5423100 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.0323. Min Range: -13.0323
Max Act: 11.9073. Min Act: -0.1700
Data Index: 3690281 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.0323. Min Range: -13.0323
Max Act: 11.9073. Min Act: -0.1700
Data Index: 3378709 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.0323. Min Range: -13.0323
Max Act: 11.9073. Min Act: -0.1700
Data Index: 8488582 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19