Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 199 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.4902. Min Act: -0.1700
Data Index: 8123046 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.4590. Min Act: -0.1700
Data Index: 2277017 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.3965. Min Act: -0.1700
Data Index: 1061352 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.3965. Min Act: -0.1700
Data Index: 1702293 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.4277. Min Act: -0.1700
Data Index: 5541398 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.4277. Min Act: -0.1700
Data Index: 6382895 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.3965. Min Act: -0.1700
Data Index: 327155 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.3965. Min Act: -0.1700
Data Index: 6422475 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.3652. Min Act: -0.1700
Data Index: 643565 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.3340. Min Act: -0.1700
Data Index: 5757385 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.3340. Min Act: -0.1700
Data Index: 8370052 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.2715. Min Act: -0.1700
Data Index: 8723671 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.3027. Min Act: -0.1700
Data Index: 118295 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.2715. Min Act: -0.1700
Data Index: 4347822 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.2715. Min Act: -0.1700
Data Index: 6578499 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.2715. Min Act: -0.1700
Data Index: 228429 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.2715. Min Act: -0.1700
Data Index: 3875069 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.2715. Min Act: -0.1700
Data Index: 5516863 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.2715. Min Act: -0.1700
Data Index: 5286907 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.2715. Min Act: -0.1700
Data Index: 674798 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19