Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5338 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0001. Min Range: -8.0001
Max Act: 8.0001. Min Act: -0.1700
Data Index: 3364902 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0001. Min Range: -8.0001
Max Act: 7.7501. Min Act: -0.1700
Data Index: 2511259 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0001. Min Range: -8.0001
Max Act: 7.7501. Min Act: -0.1700
Data Index: 408990 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0001. Min Range: -8.0001
Max Act: 7.7501. Min Act: -0.1700
Data Index: 4914115 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0001. Min Range: -8.0001
Max Act: 7.6876. Min Act: -0.1700
Data Index: 8024951 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0001. Min Range: -8.0001
Max Act: 7.6876. Min Act: -0.1700
Data Index: 8037811 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0001. Min Range: -8.0001
Max Act: 7.6251. Min Act: -0.1699
Data Index: 7069481 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0001. Min Range: -8.0001
Max Act: 7.6251. Min Act: -0.1700
Data Index: 8777538 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0001. Min Range: -8.0001
Max Act: 7.6251. Min Act: -0.1700
Data Index: 3626584 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0001. Min Range: -8.0001
Max Act: 7.5938. Min Act: -0.1700
Data Index: 5627474 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0001. Min Range: -8.0001
Max Act: 7.5001. Min Act: -0.1700
Data Index: 5300878 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0001. Min Range: -8.0001
Max Act: 7.5313. Min Act: -0.1700
Data Index: 3591008 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0001. Min Range: -8.0001
Max Act: 7.5313. Min Act: -0.1700
Data Index: 3338970 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0001. Min Range: -8.0001
Max Act: 7.5313. Min Act: -0.1700
Data Index: 2477204 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0001. Min Range: -8.0001
Max Act: 7.4688. Min Act: -0.1700
Data Index: 7914411 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0001. Min Range: -8.0001
Max Act: 7.4688. Min Act: -0.1700
Data Index: 3591016 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0001. Min Range: -8.0001
Max Act: 7.5001. Min Act: -0.1700
Data Index: 1965735 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0001. Min Range: -8.0001
Max Act: 7.4688. Min Act: -0.1700
Data Index: 8110589 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0001. Min Range: -8.0001
Max Act: 7.4376. Min Act: -0.1700
Data Index: 5921920 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0001. Min Range: -8.0001
Max Act: 7.4376. Min Act: -0.1700
Data Index: 52474 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19