Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4041 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.8243. Min Act: -0.1700
Data Index: 6489285 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.7930. Min Act: -0.1700
Data Index: 4919558 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.7618. Min Act: -0.1700
Data Index: 5612972 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.6993. Min Act: -0.1700
Data Index: 8098441 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.6993. Min Act: -0.1700
Data Index: 2052128 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.6993. Min Act: -0.1700
Data Index: 1753941 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.6368. Min Act: -0.1700
Data Index: 3183774 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.6368. Min Act: -0.1700
Data Index: 507277 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.6055. Min Act: -0.1700
Data Index: 1817459 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.6055. Min Act: -0.1700
Data Index: 4105564 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.6055. Min Act: -0.1700
Data Index: 8282367 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.5743. Min Act: -0.1700
Data Index: 3547679 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.5430. Min Act: -0.1700
Data Index: 5175439 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.5743. Min Act: -0.1700
Data Index: 6031989 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.5743. Min Act: -0.1700
Data Index: 6003703 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.5743. Min Act: -0.1700
Data Index: 508092 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.5430. Min Act: -0.1700
Data Index: 3377433 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.5118. Min Act: -0.1700
Data Index: 7637412 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.5118. Min Act: -0.1700
Data Index: 951727 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8243. Min Range: -5.8243
Max Act: 5.5430. Min Act: -0.1700
Data Index: 4115943 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19