Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4531 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4009. Min Range: -8.4009
Max Act: 8.4009. Min Act: -0.1700
Data Index: 5787395 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4009. Min Range: -8.4009
Max Act: 8.0259. Min Act: -0.1700
Data Index: 145323 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4009. Min Range: -8.4009
Max Act: 7.9634. Min Act: -0.1699
Data Index: 6254339 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4009. Min Range: -8.4009
Max Act: 7.9009. Min Act: -0.1700
Data Index: 4388682 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4009. Min Range: -8.4009
Max Act: 7.9322. Min Act: -0.1700
Data Index: 3621481 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4009. Min Range: -8.4009
Max Act: 7.8697. Min Act: -0.1698
Data Index: 37122 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4009. Min Range: -8.4009
Max Act: 7.8384. Min Act: -0.1694
Data Index: 8061283 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4009. Min Range: -8.4009
Max Act: 7.8072. Min Act: -0.1700
Data Index: 890456 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4009. Min Range: -8.4009
Max Act: 7.8072. Min Act: -0.1700
Data Index: 4931488 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4009. Min Range: -8.4009
Max Act: 7.7134. Min Act: -0.1700
Data Index: 5862859 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4009. Min Range: -8.4009
Max Act: 7.7759. Min Act: -0.1700
Data Index: 372768 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4009. Min Range: -8.4009
Max Act: 7.7447. Min Act: -0.1699
Data Index: 4882835 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4009. Min Range: -8.4009
Max Act: 7.7759. Min Act: -0.1700
Data Index: 8543142 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4009. Min Range: -8.4009
Max Act: 7.6822. Min Act: -0.1700
Data Index: 7995989 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4009. Min Range: -8.4009
Max Act: 7.7447. Min Act: -0.1700
Data Index: 6466099 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4009. Min Range: -8.4009
Max Act: 7.6822. Min Act: -0.1700
Data Index: 7521713 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4009. Min Range: -8.4009
Max Act: 7.6822. Min Act: -0.1700
Data Index: 3829192 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4009. Min Range: -8.4009
Max Act: 7.6509. Min Act: -0.1700
Data Index: 781166 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4009. Min Range: -8.4009
Max Act: 7.6822. Min Act: -0.1700
Data Index: 1768511 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4009. Min Range: -8.4009
Max Act: 7.6509. Min Act: -0.1700
Data Index: 2589593 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19