Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3657 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1717. Min Range: -12.1717
Max Act: 12.1717. Min Act: -0.1700
Data Index: 7802536 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1717. Min Range: -12.1717
Max Act: 11.9842. Min Act: -0.1700
Data Index: 6439729 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1717. Min Range: -12.1717
Max Act: 11.6092. Min Act: -0.1700
Data Index: 5201081 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1717. Min Range: -12.1717
Max Act: 11.6717. Min Act: -0.1700
Data Index: 4083603 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1717. Min Range: -12.1717
Max Act: 11.4217. Min Act: -0.1700
Data Index: 5953420 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1717. Min Range: -12.1717
Max Act: 11.4217. Min Act: -0.1700
Data Index: 7053825 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1717. Min Range: -12.1717
Max Act: 11.2967. Min Act: -0.1700
Data Index: 359799 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1717. Min Range: -12.1717
Max Act: 11.2967. Min Act: -0.1700
Data Index: 2030729 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1717. Min Range: -12.1717
Max Act: 11.2967. Min Act: -0.1700
Data Index: 5981009 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1717. Min Range: -12.1717
Max Act: 11.2967. Min Act: -0.1700
Data Index: 8662006 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1717. Min Range: -12.1717
Max Act: 11.2342. Min Act: -0.1700
Data Index: 1498134 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1717. Min Range: -12.1717
Max Act: 11.1717. Min Act: -0.1700
Data Index: 1670241 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1717. Min Range: -12.1717
Max Act: 11.1717. Min Act: -0.1700
Data Index: 7662745 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1717. Min Range: -12.1717
Max Act: 11.1717. Min Act: -0.1700
Data Index: 8290799 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1717. Min Range: -12.1717
Max Act: 11.1717. Min Act: -0.1700
Data Index: 2042539 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1717. Min Range: -12.1717
Max Act: 11.1092. Min Act: -0.1700
Data Index: 5083744 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1717. Min Range: -12.1717
Max Act: 11.1092. Min Act: -0.1700
Data Index: 7236980 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1717. Min Range: -12.1717
Max Act: 11.1092. Min Act: -0.1700
Data Index: 3161188 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1717. Min Range: -12.1717
Max Act: 11.0467. Min Act: -0.1700
Data Index: 2227155 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1717. Min Range: -12.1717
Max Act: 10.9842. Min Act: -0.1700
Data Index: 7808380 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19