Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1577 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.7898. Min Act: -0.1700
Data Index: 7885787 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.7121. Min Act: -0.1700
Data Index: 525951 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.7207. Min Act: -0.1700
Data Index: 1904573 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.7121. Min Act: -0.1700
Data Index: 3409670 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.7034. Min Act: -0.1700
Data Index: 2716306 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.6860. Min Act: -0.1700
Data Index: 6479361 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.6774. Min Act: -0.1700
Data Index: 7957428 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.6860. Min Act: -0.1700
Data Index: 1416831 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.6687. Min Act: -0.1698
Data Index: 7156619 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.6513. Min Act: -0.1700
Data Index: 8336544 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.6687. Min Act: -0.1688
Data Index: 7957426 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.6600. Min Act: -0.1700
Data Index: 4057459 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.6600. Min Act: -0.1688
Data Index: 7957425 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.6600. Min Act: -0.1700
Data Index: 4148021 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.6513. Min Act: -0.1700
Data Index: 7957427 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.6339. Min Act: -0.1700
Data Index: 7997808 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.6426. Min Act: -0.1700
Data Index: 4778084 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.6339. Min Act: -0.1700
Data Index: 933019 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.6339. Min Act: -0.1700
Data Index: 4033947 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7898. Min Range: -1.7898
Max Act: 1.6252. Min Act: -0.1700
Data Index: 8668929 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19