Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3638 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.6356. Min Act: -0.1700
Data Index: 2600915 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.5417. Min Act: -0.1700
Data Index: 5297201 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.5417. Min Act: -0.1700
Data Index: 6711546 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.5417. Min Act: -0.1700
Data Index: 2250722 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.5103. Min Act: -0.1700
Data Index: 201681 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.5103. Min Act: -0.1700
Data Index: 4158813 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.5103. Min Act: -0.1700
Data Index: 3685024 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.5103. Min Act: -0.1700
Data Index: 6008020 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.5103. Min Act: -0.1700
Data Index: 3654074 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.5103. Min Act: -0.1700
Data Index: 5485441 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.4790. Min Act: -0.1700
Data Index: 8648431 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.4790. Min Act: -0.1700
Data Index: 3035979 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.4790. Min Act: -0.1700
Data Index: 7584090 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.5103. Min Act: -0.1700
Data Index: 7516027 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.5103. Min Act: -0.1700
Data Index: 7465112 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.4790. Min Act: -0.1700
Data Index: 2314012 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.4790. Min Act: -0.1700
Data Index: 3706157 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.4790. Min Act: -0.1700
Data Index: 3924844 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.4790. Min Act: -0.1700
Data Index: 2317169 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6356. Min Range: -3.6356
Max Act: 3.4790. Min Act: -0.1700
Data Index: 4750371 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19