Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 435 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.9431. Min Act: -0.1700
Data Index: 2032227 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.9431. Min Act: -0.1700
Data Index: 1034948 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.8181. Min Act: -0.1700
Data Index: 4661589 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.8181. Min Act: -0.1700
Data Index: 7515485 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.8181. Min Act: -0.1700
Data Index: 7733630 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.7556. Min Act: -0.1700
Data Index: 1469722 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.7556. Min Act: -0.1700
Data Index: 3173779 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.6931. Min Act: -0.1700
Data Index: 2034369 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.6306. Min Act: -0.1700
Data Index: 5126959 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.6306. Min Act: -0.1700
Data Index: 5495093 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.6306. Min Act: -0.1700
Data Index: 5363544 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.5681. Min Act: -0.1700
Data Index: 5008687 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.5681. Min Act: -0.1700
Data Index: 7941586 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.5681. Min Act: -0.1700
Data Index: 2510737 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.5056. Min Act: -0.1698
Data Index: 7850003 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.5056. Min Act: -0.1700
Data Index: 5804889 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.5056. Min Act: -0.1700
Data Index: 4644005 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.5056. Min Act: -0.1700
Data Index: 2254023 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.4431. Min Act: -0.1698
Data Index: 5856042 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9431. Min Range: -10.9431
Max Act: 10.4431. Min Act: -0.1700
Data Index: 6274792 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19