Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2693 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.6283. Min Act: -0.1700
Data Index: 760188 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.5971. Min Act: -0.1700
Data Index: 2128112 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.5658. Min Act: -0.1700
Data Index: 3739372 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.4096. Min Act: -0.1700
Data Index: 7913339 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.4096. Min Act: -0.1700
Data Index: 1528888 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.3471. Min Act: -0.1700
Data Index: 8660623 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.3471. Min Act: -0.1700
Data Index: 5115075 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.3158. Min Act: -0.1700
Data Index: 8665636 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.3158. Min Act: -0.1700
Data Index: 2868222 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.3158. Min Act: -0.1700
Data Index: 488425 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.3158. Min Act: -0.1700
Data Index: 3302344 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.3158. Min Act: -0.1700
Data Index: 1342199 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.2533. Min Act: -0.1700
Data Index: 3739373 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.2221. Min Act: -0.1700
Data Index: 4815940 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.2221. Min Act: -0.1700
Data Index: 1624733 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.2221. Min Act: -0.1700
Data Index: 3856689 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.2221. Min Act: -0.1700
Data Index: 1400570 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.1908. Min Act: -0.1700
Data Index: 275884 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.1908. Min Act: -0.1700
Data Index: 2872726 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6283. Min Range: -4.6283
Max Act: 4.1908. Min Act: -0.1700
Data Index: 1929902 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19