Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.4057. Min Act: -0.1700
Data Index: 7302063 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.3566. Min Act: -0.1700
Data Index: 3029718 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.3238. Min Act: -0.1700
Data Index: 2176206 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.3074. Min Act: -0.1700
Data Index: 5350015 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.2745. Min Act: -0.1700
Data Index: 449375 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.2745. Min Act: -0.1700
Data Index: 3270105 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.2415. Min Act: -0.1700
Data Index: 109725 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.2415. Min Act: -0.1700
Data Index: 5444093 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.2580. Min Act: -0.1700
Data Index: 2656297 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.2580. Min Act: -0.1692
Data Index: 1986290 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.2249. Min Act: -0.1700
Data Index: 5435191 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.2249. Min Act: -0.1699
Data Index: 3433199 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.2249. Min Act: -0.1700
Data Index: 7250735 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.1917. Min Act: -0.1700
Data Index: 4069239 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.2083. Min Act: -0.1700
Data Index: 387407 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.2083. Min Act: -0.1700
Data Index: 7216969 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.1917. Min Act: -0.1700
Data Index: 1405396 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.1917. Min Act: -0.1700
Data Index: 5014544 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.1917. Min Act: -0.1700
Data Index: 8003986 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4057. Min Range: -2.4057
Max Act: 2.1917. Min Act: -0.1700
Data Index: 5019861 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19