Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3507 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.8334. Min Act: -0.1700
Data Index: 5414056 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.7397. Min Act: -0.1700
Data Index: 7337904 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.7397. Min Act: -0.1700
Data Index: 3681006 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.7397. Min Act: -0.1700
Data Index: 6253598 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.7084. Min Act: -0.1700
Data Index: 7138966 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.7084. Min Act: -0.1700
Data Index: 5566861 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.7084. Min Act: -0.1700
Data Index: 7117760 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.7084. Min Act: -0.1700
Data Index: 3807416 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.6459. Min Act: -0.1700
Data Index: 660813 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.6772. Min Act: -0.1700
Data Index: 821563 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.6772. Min Act: -0.1700
Data Index: 6883820 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.6459. Min Act: -0.1700
Data Index: 7805200 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.6459. Min Act: -0.1700
Data Index: 5074460 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.6147. Min Act: -0.1700
Data Index: 7718611 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.6147. Min Act: -0.1700
Data Index: 6648709 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.6147. Min Act: -0.1700
Data Index: 6106631 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.6147. Min Act: -0.1700
Data Index: 1887370 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.5834. Min Act: -0.1700
Data Index: 1840041 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.5834. Min Act: -0.1700
Data Index: 201848 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8334. Min Range: -5.8334
Max Act: 5.5834. Min Act: -0.1700
Data Index: 2593390 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19