Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2424 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.9297. Min Act: -0.1700
Data Index: 2242676 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.6797. Min Act: -0.1700
Data Index: 5873105 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.5234. Min Act: -0.1700
Data Index: 6614121 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.5547. Min Act: -0.1700
Data Index: 5185313 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.5234. Min Act: -0.1700
Data Index: 2278352 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.4922. Min Act: -0.1700
Data Index: 626122 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.4922. Min Act: -0.1700
Data Index: 2396843 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.4609. Min Act: -0.1700
Data Index: 3447197 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.3984. Min Act: -0.1700
Data Index: 1637003 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.3359. Min Act: -0.1700
Data Index: 5735442 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.3672. Min Act: -0.1700
Data Index: 2717685 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.3359. Min Act: -0.1700
Data Index: 8718438 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.3672. Min Act: -0.1700
Data Index: 2325465 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.3359. Min Act: -0.1700
Data Index: 3045340 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.3047. Min Act: -0.1700
Data Index: 5912317 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.3047. Min Act: -0.1700
Data Index: 8357663 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.3047. Min Act: -0.1700
Data Index: 4535988 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.2734. Min Act: -0.1700
Data Index: 2704952 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.2734. Min Act: -0.1700
Data Index: 698073 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9297. Min Range: -6.9297
Max Act: 6.2422. Min Act: -0.1700
Data Index: 2051461 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19