Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4434 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1829. Min Range: -10.1829
Max Act: 10.1829. Min Act: -0.1700
Data Index: 1942017 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1829. Min Range: -10.1829
Max Act: 9.7454. Min Act: -0.1700
Data Index: 2846458 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1829. Min Range: -10.1829
Max Act: 9.6829. Min Act: -0.1700
Data Index: 7257950 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1829. Min Range: -10.1829
Max Act: 9.6204. Min Act: -0.1700
Data Index: 4620662 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1829. Min Range: -10.1829
Max Act: 9.4954. Min Act: -0.1700
Data Index: 7990223 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1829. Min Range: -10.1829
Max Act: 9.4954. Min Act: -0.1700
Data Index: 4430068 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1829. Min Range: -10.1829
Max Act: 9.4329. Min Act: -0.1700
Data Index: 4694911 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1829. Min Range: -10.1829
Max Act: 9.4329. Min Act: -0.1700
Data Index: 6919768 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1829. Min Range: -10.1829
Max Act: 9.4329. Min Act: -0.1700
Data Index: 4207411 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1829. Min Range: -10.1829
Max Act: 9.4329. Min Act: -0.1700
Data Index: 7597617 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1829. Min Range: -10.1829
Max Act: 9.4329. Min Act: -0.1700
Data Index: 857772 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1829. Min Range: -10.1829
Max Act: 9.4329. Min Act: -0.1700
Data Index: 3621068 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1829. Min Range: -10.1829
Max Act: 9.3704. Min Act: -0.1700
Data Index: 5793999 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1829. Min Range: -10.1829
Max Act: 9.3704. Min Act: -0.1700
Data Index: 816992 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1829. Min Range: -10.1829
Max Act: 9.2454. Min Act: -0.1700
Data Index: 7238159 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1829. Min Range: -10.1829
Max Act: 9.3079. Min Act: -0.1700
Data Index: 3816339 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1829. Min Range: -10.1829
Max Act: 9.3079. Min Act: -0.1700
Data Index: 5124681 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1829. Min Range: -10.1829
Max Act: 9.3079. Min Act: -0.1700
Data Index: 4983776 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1829. Min Range: -10.1829
Max Act: 9.3079. Min Act: -0.1700
Data Index: 2093032 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1829. Min Range: -10.1829
Max Act: 9.3079. Min Act: -0.1700
Data Index: 2554152 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19