Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2770 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.0220. Min Range: -1.0220
Max Act: 1.0220. Min Act: -0.1700
Data Index: 1581409 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0220. Min Range: -1.0220
Max Act: 1.0220. Min Act: -0.1700
Data Index: 6328552 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0220. Min Range: -1.0220
Max Act: 0.9699. Min Act: -0.1700
Data Index: 6636425 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0220. Min Range: -1.0220
Max Act: 0.9786. Min Act: -0.1700
Data Index: 6197592 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0220. Min Range: -1.0220
Max Act: 0.9699. Min Act: -0.1700
Data Index: 4976599 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0220. Min Range: -1.0220
Max Act: 0.9613. Min Act: -0.1700
Data Index: 1957187 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0220. Min Range: -1.0220
Max Act: 0.9527. Min Act: -0.1700
Data Index: 8168355 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0220. Min Range: -1.0220
Max Act: 0.9613. Min Act: -0.1700
Data Index: 7453392 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0220. Min Range: -1.0220
Max Act: 0.9527. Min Act: -0.1700
Data Index: 5892440 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0220. Min Range: -1.0220
Max Act: 0.9527. Min Act: -0.1700
Data Index: 2264569 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0220. Min Range: -1.0220
Max Act: 0.9613. Min Act: -0.1700
Data Index: 3739659 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0220. Min Range: -1.0220
Max Act: 0.9354. Min Act: -0.1700
Data Index: 8315158 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0220. Min Range: -1.0220
Max Act: 0.9441. Min Act: -0.1700
Data Index: 6615114 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0220. Min Range: -1.0220
Max Act: 0.9527. Min Act: -0.1700
Data Index: 5876266 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0220. Min Range: -1.0220
Max Act: 0.9441. Min Act: -0.1700
Data Index: 1256925 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0220. Min Range: -1.0220
Max Act: 0.9441. Min Act: -0.1700
Data Index: 5865040 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0220. Min Range: -1.0220
Max Act: 0.9354. Min Act: -0.1700
Data Index: 8125998 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0220. Min Range: -1.0220
Max Act: 0.9354. Min Act: -0.1700
Data Index: 1342118 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0220. Min Range: -1.0220
Max Act: 0.9441. Min Act: -0.1700
Data Index: 6907208 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0220. Min Range: -1.0220
Max Act: 0.9354. Min Act: -0.1700
Data Index: 45041 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19