Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4399 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.6754. Min Act: -0.1700
Data Index: 3104971 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.6129. Min Act: -0.1700
Data Index: 3144999 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.4879. Min Act: -0.1700
Data Index: 6145667 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.4254. Min Act: -0.1700
Data Index: 4732 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.4566. Min Act: -0.1700
Data Index: 5171273 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.4254. Min Act: -0.1700
Data Index: 2836086 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.4254. Min Act: -0.1700
Data Index: 8085267 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.3629. Min Act: -0.1700
Data Index: 5176292 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.3004. Min Act: -0.1700
Data Index: 4114734 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.2691. Min Act: -0.1700
Data Index: 8073659 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.2691. Min Act: -0.1700
Data Index: 2172083 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.2691. Min Act: -0.1700
Data Index: 8521545 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.2379. Min Act: -0.1700
Data Index: 2788976 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.2379. Min Act: -0.1700
Data Index: 6686635 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.2379. Min Act: -0.1700
Data Index: 868091 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.2379. Min Act: -0.1700
Data Index: 7418997 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.2066. Min Act: -0.1700
Data Index: 7128865 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.2066. Min Act: -0.1700
Data Index: 4761756 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.2066. Min Act: -0.1700
Data Index: 1450900 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6754. Min Range: -7.6754
Max Act: 7.1441. Min Act: -0.1700
Data Index: 7937772 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19