Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 320 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.8467. Min Act: -0.1700
Data Index: 5121538 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5654. Min Act: -0.1700
Data Index: 5263419 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5342. Min Act: -0.1700
Data Index: 1153055 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5342. Min Act: -0.1700
Data Index: 3070216 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5029. Min Act: -0.1700
Data Index: 4295051 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5029. Min Act: -0.1700
Data Index: 750147 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.4717. Min Act: -0.1700
Data Index: 1558290 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.4717. Min Act: -0.1700
Data Index: 4564993 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.4404. Min Act: -0.1700
Data Index: 1649522 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.4404. Min Act: -0.1700
Data Index: 929046 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.4404. Min Act: -0.1700
Data Index: 7967385 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.4092. Min Act: -0.1700
Data Index: 229792 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.4092. Min Act: -0.1700
Data Index: 7803561 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.4404. Min Act: -0.1700
Data Index: 7971639 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.4092. Min Act: -0.1700
Data Index: 4105703 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.3779. Min Act: -0.1700
Data Index: 3561622 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.3779. Min Act: -0.1700
Data Index: 2872386 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.3779. Min Act: -0.1700
Data Index: 1058912 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.3779. Min Act: -0.1700
Data Index: 6967105 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.3779. Min Act: -0.1700
Data Index: 625279 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19