Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5684 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.1717. Min Act: -0.1700
Data Index: 2115493 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.1245. Min Act: -0.1700
Data Index: 2380685 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.0614. Min Act: -0.1700
Data Index: 3393959 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.9350. Min Act: -0.1700
Data Index: 8811209 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.9350. Min Act: -0.1700
Data Index: 5228721 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.9191. Min Act: -0.1700
Data Index: 3846794 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.9191. Min Act: -0.1700
Data Index: 1462718 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.9191. Min Act: -0.1700
Data Index: 7116979 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.9191. Min Act: -0.1700
Data Index: 7978234 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.9033. Min Act: -0.1700
Data Index: 6041610 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.9033. Min Act: -0.1700
Data Index: 3920614 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.9033. Min Act: -0.1700
Data Index: 2064630 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.8874. Min Act: -0.1700
Data Index: 7226669 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.8557. Min Act: -0.1700
Data Index: 6480286 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.8557. Min Act: -0.1700
Data Index: 3183676 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.8398. Min Act: -0.1700
Data Index: 5765849 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.8398. Min Act: -0.1700
Data Index: 3979853 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.8239. Min Act: -0.1700
Data Index: 6038963 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.8239. Min Act: -0.1700
Data Index: 4269851 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.8080. Min Act: -0.1700
Data Index: 5025466 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19