Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4165 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.8395. Min Act: -0.1700
Data Index: 7399067 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.8083. Min Act: -0.1700
Data Index: 3491061 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.7770. Min Act: -0.1700
Data Index: 3565563 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.6831. Min Act: -0.1700
Data Index: 2762847 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.6205. Min Act: -0.1700
Data Index: 3612433 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.5892. Min Act: -0.1700
Data Index: 6674368 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.5892. Min Act: -0.1700
Data Index: 4139972 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.5266. Min Act: -0.1700
Data Index: 1064072 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.5266. Min Act: -0.1700
Data Index: 4778410 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.5266. Min Act: -0.1700
Data Index: 5614083 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.4953. Min Act: -0.1700
Data Index: 3986030 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.4326. Min Act: -0.1700
Data Index: 2226030 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.4326. Min Act: -0.1700
Data Index: 8159937 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.3699. Min Act: -0.1700
Data Index: 5319246 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.3699. Min Act: -0.1700
Data Index: 7399069 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.3385. Min Act: -0.1700
Data Index: 5838808 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.3072. Min Act: -0.1700
Data Index: 7399068 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.3229. Min Act: -0.1700
Data Index: 4661530 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.3072. Min Act: -0.1700
Data Index: 4133908 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8395. Min Range: -3.8395
Max Act: 3.2915. Min Act: -0.1700
Data Index: 2960072 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19