Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3899 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.2682. Min Act: -0.1700
Data Index: 2243300 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.2517. Min Act: -0.1700
Data Index: 558885 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.2186. Min Act: -0.1700
Data Index: 8084786 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.2020. Min Act: -0.1700
Data Index: 8571216 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.2020. Min Act: -0.1700
Data Index: 6094369 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.1688. Min Act: -0.1700
Data Index: 3709670 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.1688. Min Act: -0.1700
Data Index: 1575679 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.1688. Min Act: -0.1700
Data Index: 479501 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.1521. Min Act: -0.1700
Data Index: 2047097 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.1354. Min Act: -0.1700
Data Index: 2901216 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.1354. Min Act: -0.1700
Data Index: 1306116 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.1354. Min Act: -0.1700
Data Index: 5901936 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.1354. Min Act: -0.1700
Data Index: 8350658 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.1354. Min Act: -0.1700
Data Index: 7881365 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.1354. Min Act: -0.1700
Data Index: 2335487 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.1187. Min Act: -0.1700
Data Index: 8361538 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.1187. Min Act: -0.1700
Data Index: 1477626 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.1187. Min Act: -0.1700
Data Index: 1195110 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.1187. Min Act: -0.1700
Data Index: 1967138 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2682. Min Range: -2.2682
Max Act: 2.1187. Min Act: -0.1700
Data Index: 98244 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19