Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 659 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7347. Min Range: -8.7347
Max Act: 8.7347. Min Act: -0.1700
Data Index: 6726991 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7347. Min Range: -8.7347
Max Act: 8.4222. Min Act: -0.1700
Data Index: 6101887 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7347. Min Range: -8.7347
Max Act: 8.4847. Min Act: -0.1700
Data Index: 246667 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7347. Min Range: -8.7347
Max Act: 8.3597. Min Act: -0.1700
Data Index: 2671815 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7347. Min Range: -8.7347
Max Act: 8.2972. Min Act: -0.1700
Data Index: 4555730 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7347. Min Range: -8.7347
Max Act: 8.2347. Min Act: -0.1700
Data Index: 1856658 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7347. Min Range: -8.7347
Max Act: 8.1722. Min Act: -0.1700
Data Index: 3369995 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7347. Min Range: -8.7347
Max Act: 8.1722. Min Act: -0.1700
Data Index: 3999336 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7347. Min Range: -8.7347
Max Act: 8.1722. Min Act: -0.1700
Data Index: 4237538 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7347. Min Range: -8.7347
Max Act: 8.1097. Min Act: -0.1700
Data Index: 2432065 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7347. Min Range: -8.7347
Max Act: 8.1722. Min Act: -0.1700
Data Index: 5155180 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7347. Min Range: -8.7347
Max Act: 8.0472. Min Act: -0.1700
Data Index: 2001012 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7347. Min Range: -8.7347
Max Act: 8.0159. Min Act: -0.1700
Data Index: 2211617 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7347. Min Range: -8.7347
Max Act: 7.9847. Min Act: -0.1700
Data Index: 5242451 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7347. Min Range: -8.7347
Max Act: 7.9847. Min Act: -0.1700
Data Index: 7356111 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7347. Min Range: -8.7347
Max Act: 7.9534. Min Act: -0.1700
Data Index: 4633548 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7347. Min Range: -8.7347
Max Act: 7.9222. Min Act: -0.1700
Data Index: 6352041 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7347. Min Range: -8.7347
Max Act: 7.8909. Min Act: -0.1700
Data Index: 4167228 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7347. Min Range: -8.7347
Max Act: 7.8909. Min Act: -0.1700
Data Index: 35501 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7347. Min Range: -8.7347
Max Act: 7.8909. Min Act: -0.1700
Data Index: 4782365 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19