Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1243 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.6902. Min Act: -0.1700
Data Index: 2131747 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.4714. Min Act: -0.1700
Data Index: 2276104 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.4714. Min Act: -0.1700
Data Index: 3819617 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.4089. Min Act: -0.1700
Data Index: 444022 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.3777. Min Act: -0.1700
Data Index: 4584479 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.3777. Min Act: -0.1700
Data Index: 5359710 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.3152. Min Act: -0.1700
Data Index: 165985 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.3152. Min Act: -0.1700
Data Index: 5542358 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.3152. Min Act: -0.1700
Data Index: 1502187 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.3152. Min Act: -0.1700
Data Index: 772676 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.3152. Min Act: -0.1700
Data Index: 1192775 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.3152. Min Act: -0.1700
Data Index: 1167845 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.3464. Min Act: -0.1700
Data Index: 2327131 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.2839. Min Act: -0.1700
Data Index: 7223661 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.2839. Min Act: -0.1700
Data Index: 540856 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.2526. Min Act: -0.1700
Data Index: 4633487 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.2214. Min Act: -0.1700
Data Index: 5330739 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.2214. Min Act: -0.1700
Data Index: 4355564 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.1901. Min Act: -0.1700
Data Index: 1354751 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.1901. Min Act: -0.1700
Data Index: 4919816 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19