Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2535 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3075. Min Range: -8.3075
Max Act: 8.3075. Min Act: -0.1700
Data Index: 3946225 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3075. Min Range: -8.3075
Max Act: 8.2450. Min Act: -0.1700
Data Index: 1656358 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3075. Min Range: -8.3075
Max Act: 7.9950. Min Act: -0.1700
Data Index: 8190058 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3075. Min Range: -8.3075
Max Act: 7.9950. Min Act: -0.1700
Data Index: 3232107 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3075. Min Range: -8.3075
Max Act: 7.9950. Min Act: -0.1700
Data Index: 546494 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3075. Min Range: -8.3075
Max Act: 7.9325. Min Act: -0.1700
Data Index: 1569761 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3075. Min Range: -8.3075
Max Act: 7.9325. Min Act: -0.1700
Data Index: 6982564 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3075. Min Range: -8.3075
Max Act: 7.9325. Min Act: -0.1700
Data Index: 1674666 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3075. Min Range: -8.3075
Max Act: 7.9325. Min Act: -0.1700
Data Index: 5784960 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3075. Min Range: -8.3075
Max Act: 7.8700. Min Act: -0.1700
Data Index: 6270818 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3075. Min Range: -8.3075
Max Act: 7.8700. Min Act: -0.1700
Data Index: 2830316 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3075. Min Range: -8.3075
Max Act: 7.8700. Min Act: -0.1700
Data Index: 1435189 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3075. Min Range: -8.3075
Max Act: 7.8700. Min Act: -0.1700
Data Index: 8599868 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3075. Min Range: -8.3075
Max Act: 7.8075. Min Act: -0.1700
Data Index: 7652034 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3075. Min Range: -8.3075
Max Act: 7.8075. Min Act: -0.1700
Data Index: 3275621 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3075. Min Range: -8.3075
Max Act: 7.8075. Min Act: -0.1700
Data Index: 5221334 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3075. Min Range: -8.3075
Max Act: 7.8075. Min Act: -0.1700
Data Index: 1749545 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3075. Min Range: -8.3075
Max Act: 7.8075. Min Act: -0.1700
Data Index: 3470519 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3075. Min Range: -8.3075
Max Act: 7.7450. Min Act: -0.1700
Data Index: 7182300 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3075. Min Range: -8.3075
Max Act: 7.7450. Min Act: -0.1700
Data Index: 3852634 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19