Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3212 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.7173. Min Act: -0.1700
Data Index: 3604971 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.6860. Min Act: -0.1700
Data Index: 8781149 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.6235. Min Act: -0.1700
Data Index: 3377974 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.5610. Min Act: -0.1700
Data Index: 8781158 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.5610. Min Act: -0.1700
Data Index: 406303 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.5298. Min Act: -0.1700
Data Index: 2289720 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.4985. Min Act: -0.1700
Data Index: 1495217 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.4985. Min Act: -0.1700
Data Index: 6207948 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.4985. Min Act: -0.1700
Data Index: 373460 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.4360. Min Act: -0.1700
Data Index: 7787437 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.4360. Min Act: -0.1700
Data Index: 4282025 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.4048. Min Act: -0.1700
Data Index: 1495203 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.4360. Min Act: -0.1700
Data Index: 2264945 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.4048. Min Act: -0.1700
Data Index: 373474 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.3110. Min Act: -0.1700
Data Index: 404189 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.2798. Min Act: -0.1700
Data Index: 6332081 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.2485. Min Act: -0.1700
Data Index: 7004742 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.2173. Min Act: -0.1700
Data Index: 6207938 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.2485. Min Act: -0.1700
Data Index: 4242019 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7173. Min Range: -6.7173
Max Act: 6.2485. Min Act: -0.1700
Data Index: 2206972 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19