Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3664 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.4060. Min Act: -0.1700
Data Index: 5913501 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.3897. Min Act: -0.1700
Data Index: 4395461 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.3406. Min Act: -0.1700
Data Index: 8638375 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.2913. Min Act: -0.1700
Data Index: 4122312 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.3078. Min Act: -0.1700
Data Index: 8045203 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.2913. Min Act: -0.1700
Data Index: 4574856 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.3078. Min Act: -0.1700
Data Index: 7530706 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.2749. Min Act: -0.1700
Data Index: 8105971 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.2584. Min Act: -0.1700
Data Index: 44919 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.2584. Min Act: -0.1700
Data Index: 1974309 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.2584. Min Act: -0.1700
Data Index: 5682078 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.2749. Min Act: -0.1700
Data Index: 8491903 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.2749. Min Act: -0.1700
Data Index: 2524674 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.2418. Min Act: -0.1700
Data Index: 6458749 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.2253. Min Act: -0.1700
Data Index: 7980583 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.2253. Min Act: -0.1700
Data Index: 1774020 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.2253. Min Act: -0.1700
Data Index: 5566062 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.2253. Min Act: -0.1700
Data Index: 7478561 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.2087. Min Act: -0.1700
Data Index: 7149147 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4060. Min Range: -2.4060
Max Act: 2.2253. Min Act: -0.1700
Data Index: 4811103 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19