Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4037 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.7409. Min Act: -0.1700
Data Index: 5928222 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.7096. Min Act: -0.1700
Data Index: 4204801 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.5534. Min Act: -0.1700
Data Index: 994019 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.5534. Min Act: -0.1700
Data Index: 30837 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.5221. Min Act: -0.1700
Data Index: 4638463 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.5221. Min Act: -0.1700
Data Index: 559761 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.5221. Min Act: -0.1700
Data Index: 3436524 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.4909. Min Act: -0.1700
Data Index: 755412 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.4284. Min Act: -0.1700
Data Index: 4465781 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.3659. Min Act: -0.1700
Data Index: 203829 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.3346. Min Act: -0.1700
Data Index: 8033196 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.3346. Min Act: -0.1700
Data Index: 8674427 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.3034. Min Act: -0.1700
Data Index: 6991131 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.2409. Min Act: -0.1700
Data Index: 1365080 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.2409. Min Act: -0.1700
Data Index: 5661498 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.2409. Min Act: -0.1700
Data Index: 8193688 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.2409. Min Act: -0.1700
Data Index: 8466450 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.2409. Min Act: -0.1700
Data Index: 2782569 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.2096. Min Act: -0.1700
Data Index: 6524081 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7409. Min Range: -5.7409
Max Act: 5.2096. Min Act: -0.1700
Data Index: 8597167 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19