Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.4565. Min Act: -0.1700
Data Index: 994340 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.3003. Min Act: -0.1700
Data Index: 212466 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.2378. Min Act: -0.1700
Data Index: 2921708 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.2690. Min Act: -0.1700
Data Index: 5516944 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.2378. Min Act: -0.1700
Data Index: 7703443 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.2065. Min Act: -0.1700
Data Index: 1653978 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.1753. Min Act: -0.1700
Data Index: 5475221 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.1440. Min Act: -0.1700
Data Index: 1653994 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.1753. Min Act: -0.1700
Data Index: 8429170 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.1440. Min Act: -0.1700
Data Index: 1653993 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.1440. Min Act: -0.1700
Data Index: 6076801 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.1128. Min Act: -0.1700
Data Index: 1653977 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.1128. Min Act: -0.1700
Data Index: 6041841 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.1128. Min Act: -0.1700
Data Index: 8417540 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.1440. Min Act: -0.1700
Data Index: 5418123 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.1440. Min Act: -0.1700
Data Index: 1653985 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.1128. Min Act: -0.1700
Data Index: 534960 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.0815. Min Act: -0.1700
Data Index: 1654000 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.1128. Min Act: -0.1700
Data Index: 5425624 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4565. Min Range: -4.4565
Max Act: 4.0815. Min Act: -0.1700
Data Index: 2482280 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19