Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4938 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.8358. Min Act: -0.1700
Data Index: 8111653 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.8045. Min Act: -0.1700
Data Index: 4312353 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.7733. Min Act: -0.1699
Data Index: 8741689 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.7733. Min Act: -0.1700
Data Index: 6081585 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.7420. Min Act: -0.1700
Data Index: 4502663 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.7420. Min Act: -0.1700
Data Index: 6721563 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.7733. Min Act: -0.1700
Data Index: 5824656 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.7420. Min Act: -0.1700
Data Index: 2820849 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.7420. Min Act: -0.1700
Data Index: 5737630 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.7420. Min Act: -0.1700
Data Index: 5200424 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.7420. Min Act: -0.1700
Data Index: 5173252 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.7420. Min Act: -0.1700
Data Index: 4553484 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.7420. Min Act: -0.1700
Data Index: 8116248 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.7733. Min Act: -0.1700
Data Index: 3812063 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.7420. Min Act: -0.1700
Data Index: 6918709 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.7108. Min Act: -0.1700
Data Index: 1745566 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.7108. Min Act: -0.1700
Data Index: 4890984 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.7108. Min Act: -0.1700
Data Index: 2687160 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.7420. Min Act: -0.1700
Data Index: 4678173 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8358. Min Range: -5.8358
Max Act: 5.7108. Min Act: -0.1700
Data Index: 3031901 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19