Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3396 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.7482. Min Act: -0.1700
Data Index: 937301 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.7309. Min Act: -0.1699
Data Index: 7182890 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.6963. Min Act: -0.1645
Data Index: 2540125 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.6876. Min Act: -0.1700
Data Index: 441782 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.6702. Min Act: -0.1700
Data Index: 8780320 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.6615. Min Act: -0.1658
Data Index: 3390657 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.6615. Min Act: -0.1700
Data Index: 2665601 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.6528. Min Act: -0.1692
Data Index: 3705166 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.6615. Min Act: -0.1678
Data Index: 4340222 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.6528. Min Act: -0.1699
Data Index: 4199345 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.6354. Min Act: -0.1599
Data Index: 624410 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.6354. Min Act: -0.1700
Data Index: 3048861 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.6354. Min Act: -0.1650
Data Index: 2561220 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.6354. Min Act: -0.1658
Data Index: 6600643 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.6354. Min Act: -0.1695
Data Index: 6092199 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.6354. Min Act: -0.1658
Data Index: 6015761 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.6354. Min Act: -0.1699
Data Index: 6593937 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.6267. Min Act: -0.1697
Data Index: 8508889 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.6354. Min Act: -0.1626
Data Index: 1726210 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7482. Min Range: -1.7482
Max Act: 1.6354. Min Act: -0.1700
Data Index: 5290312 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19