Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3403 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0534. Min Range: -6.0534
Max Act: 6.0534. Min Act: -0.1700
Data Index: 7401806 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0534. Min Range: -6.0534
Max Act: 5.8346. Min Act: -0.1700
Data Index: 5109682 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0534. Min Range: -6.0534
Max Act: 5.8034. Min Act: -0.1700
Data Index: 1967509 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0534. Min Range: -6.0534
Max Act: 5.6159. Min Act: -0.1700
Data Index: 1387348 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0534. Min Range: -6.0534
Max Act: 5.6159. Min Act: -0.1700
Data Index: 1915207 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0534. Min Range: -6.0534
Max Act: 5.5534. Min Act: -0.1700
Data Index: 2090593 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0534. Min Range: -6.0534
Max Act: 5.5534. Min Act: -0.1700
Data Index: 6761344 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0534. Min Range: -6.0534
Max Act: 5.5221. Min Act: -0.1700
Data Index: 8023344 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0534. Min Range: -6.0534
Max Act: 5.4596. Min Act: -0.1700
Data Index: 1621173 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0534. Min Range: -6.0534
Max Act: 5.4596. Min Act: -0.1700
Data Index: 6296151 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0534. Min Range: -6.0534
Max Act: 5.4596. Min Act: -0.1700
Data Index: 7700665 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0534. Min Range: -6.0534
Max Act: 5.4284. Min Act: -0.1700
Data Index: 1809724 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0534. Min Range: -6.0534
Max Act: 5.4284. Min Act: -0.1700
Data Index: 5782859 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0534. Min Range: -6.0534
Max Act: 5.4284. Min Act: -0.1700
Data Index: 62549 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0534. Min Range: -6.0534
Max Act: 5.3971. Min Act: -0.1700
Data Index: 1844712 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0534. Min Range: -6.0534
Max Act: 5.3971. Min Act: -0.1700
Data Index: 8385604 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0534. Min Range: -6.0534
Max Act: 5.3659. Min Act: -0.1700
Data Index: 7218566 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0534. Min Range: -6.0534
Max Act: 5.3659. Min Act: -0.1700
Data Index: 2668427 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0534. Min Range: -6.0534
Max Act: 5.3346. Min Act: -0.1700
Data Index: 7613120 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0534. Min Range: -6.0534
Max Act: 5.3971. Min Act: -0.1700
Data Index: 3618860 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19