Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3889 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.0229. Min Range: -1.0229
Max Act: 1.0229. Min Act: -0.1700
Data Index: 7780015 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0229. Min Range: -1.0229
Max Act: 0.9709. Min Act: -0.1700
Data Index: 5824247 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0229. Min Range: -1.0229
Max Act: 0.9450. Min Act: -0.1700
Data Index: 7595898 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0229. Min Range: -1.0229
Max Act: 0.9192. Min Act: -0.1700
Data Index: 2383270 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0229. Min Range: -1.0229
Max Act: 0.9192. Min Act: -0.1700
Data Index: 8360392 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0229. Min Range: -1.0229
Max Act: 0.9192. Min Act: -0.1700
Data Index: 5568625 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0229. Min Range: -1.0229
Max Act: 0.9192. Min Act: -0.1700
Data Index: 6742028 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0229. Min Range: -1.0229
Max Act: 0.9192. Min Act: -0.1700
Data Index: 6403452 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0229. Min Range: -1.0229
Max Act: 0.9192. Min Act: -0.1700
Data Index: 4437378 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0229. Min Range: -1.0229
Max Act: 0.9021. Min Act: -0.1691
Data Index: 2651786 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0229. Min Range: -1.0229
Max Act: 0.9192. Min Act: -0.1700
Data Index: 2407035 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0229. Min Range: -1.0229
Max Act: 0.9021. Min Act: -0.1700
Data Index: 7614030 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0229. Min Range: -1.0229
Max Act: 0.8679. Min Act: -0.1700
Data Index: 373913 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0229. Min Range: -1.0229
Max Act: 0.8935. Min Act: -0.1700
Data Index: 4663233 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0229. Min Range: -1.0229
Max Act: 0.8850. Min Act: -0.1700
Data Index: 5132808 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0229. Min Range: -1.0229
Max Act: 0.8850. Min Act: -0.1700
Data Index: 5395407 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0229. Min Range: -1.0229
Max Act: 0.8850. Min Act: -0.1700
Data Index: 5434761 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0229. Min Range: -1.0229
Max Act: 0.8679. Min Act: -0.1700
Data Index: 3160575 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0229. Min Range: -1.0229
Max Act: 0.8850. Min Act: -0.1700
Data Index: 1780350 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0229. Min Range: -1.0229
Max Act: 0.8765. Min Act: -0.1700
Data Index: 3731838 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19