Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3275 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.7868. Min Act: -0.1700
Data Index: 5727986 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.7243. Min Act: -0.1700
Data Index: 6898992 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.5368. Min Act: -0.1700
Data Index: 5096136 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.4431. Min Act: -0.1700
Data Index: 570821 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.3493. Min Act: -0.1700
Data Index: 3410507 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.2868. Min Act: -0.1700
Data Index: 5894339 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.2868. Min Act: -0.1700
Data Index: 7054871 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.1931. Min Act: -0.1700
Data Index: 657715 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.1618. Min Act: -0.1700
Data Index: 7810753 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.1618. Min Act: -0.1700
Data Index: 5028189 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.1306. Min Act: -0.1700
Data Index: 6336069 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.0993. Min Act: -0.1700
Data Index: 318230 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.0993. Min Act: -0.1700
Data Index: 6831526 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.1306. Min Act: -0.1700
Data Index: 7906974 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.0681. Min Act: -0.1700
Data Index: 6863077 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.0681. Min Act: -0.1700
Data Index: 5998013 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.0681. Min Act: -0.1700
Data Index: 5397451 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.0368. Min Act: -0.1700
Data Index: 7310632 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.0368. Min Act: -0.1700
Data Index: 1260722 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7868. Min Range: -6.7868
Max Act: 6.0368. Min Act: -0.1700
Data Index: 7308139 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19