Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4520 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3615. Min Range: -7.3615
Max Act: 7.3615. Min Act: -0.1700
Data Index: 6113094 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3615. Min Range: -7.3615
Max Act: 7.2053. Min Act: -0.1700
Data Index: 7606270 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3615. Min Range: -7.3615
Max Act: 7.2053. Min Act: -0.1700
Data Index: 6703710 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3615. Min Range: -7.3615
Max Act: 7.1115. Min Act: -0.1700
Data Index: 79169 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3615. Min Range: -7.3615
Max Act: 7.1428. Min Act: -0.1700
Data Index: 3269357 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3615. Min Range: -7.3615
Max Act: 7.1115. Min Act: -0.1700
Data Index: 7899309 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3615. Min Range: -7.3615
Max Act: 7.1115. Min Act: -0.1700
Data Index: 3786313 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3615. Min Range: -7.3615
Max Act: 7.0803. Min Act: -0.1700
Data Index: 3945494 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3615. Min Range: -7.3615
Max Act: 7.0490. Min Act: -0.1700
Data Index: 8222006 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3615. Min Range: -7.3615
Max Act: 7.0490. Min Act: -0.1700
Data Index: 2002819 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3615. Min Range: -7.3615
Max Act: 7.0178. Min Act: -0.1700
Data Index: 6585701 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3615. Min Range: -7.3615
Max Act: 6.9865. Min Act: -0.1700
Data Index: 528941 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3615. Min Range: -7.3615
Max Act: 6.9240. Min Act: -0.1700
Data Index: 7371705 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3615. Min Range: -7.3615
Max Act: 6.9240. Min Act: -0.1700
Data Index: 6660989 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3615. Min Range: -7.3615
Max Act: 6.9240. Min Act: -0.1700
Data Index: 2397945 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3615. Min Range: -7.3615
Max Act: 6.8928. Min Act: -0.1700
Data Index: 4713404 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3615. Min Range: -7.3615
Max Act: 6.8928. Min Act: -0.1700
Data Index: 2147098 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3615. Min Range: -7.3615
Max Act: 6.8928. Min Act: -0.1700
Data Index: 4110935 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3615. Min Range: -7.3615
Max Act: 6.8928. Min Act: -0.1700
Data Index: 4612891 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3615. Min Range: -7.3615
Max Act: 6.8928. Min Act: -0.1700
Data Index: 2093961 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19