Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1814 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.7582. Min Act: -0.1700
Data Index: 6216231 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.7422. Min Act: -0.1700
Data Index: 8028663 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.7103. Min Act: -0.1700
Data Index: 5351699 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.6943. Min Act: -0.1700
Data Index: 5879056 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.6462. Min Act: -0.1700
Data Index: 8823379 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.6141. Min Act: -0.1700
Data Index: 3925212 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.6141. Min Act: -0.1700
Data Index: 3428555 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.6141. Min Act: -0.1700
Data Index: 5645567 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.5980. Min Act: -0.1700
Data Index: 3790830 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.5980. Min Act: -0.1700
Data Index: 5034432 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.5819. Min Act: -0.1700
Data Index: 5038483 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.5657. Min Act: -0.1700
Data Index: 4780061 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.5657. Min Act: -0.1700
Data Index: 5370194 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.5335. Min Act: -0.1700
Data Index: 41624 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.5335. Min Act: -0.1700
Data Index: 7126828 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.5496. Min Act: -0.1700
Data Index: 7320791 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.5657. Min Act: -0.1700
Data Index: 7960706 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.5335. Min Act: -0.1700
Data Index: 453458 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.5496. Min Act: -0.1700
Data Index: 2561605 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7582. Min Range: -2.7582
Max Act: 2.5496. Min Act: -0.1700
Data Index: 49664 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19