Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3021 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1664. Min Range: -6.1664
Max Act: 6.1664. Min Act: -0.1700
Data Index: 5786480 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1664. Min Range: -6.1664
Max Act: 5.9476. Min Act: -0.1700
Data Index: 2699617 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1664. Min Range: -6.1664
Max Act: 5.7601. Min Act: -0.1700
Data Index: 3903610 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1664. Min Range: -6.1664
Max Act: 5.7289. Min Act: -0.1700
Data Index: 578806 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1664. Min Range: -6.1664
Max Act: 5.7289. Min Act: -0.1700
Data Index: 6583335 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1664. Min Range: -6.1664
Max Act: 5.7289. Min Act: -0.1700
Data Index: 6973078 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1664. Min Range: -6.1664
Max Act: 5.6976. Min Act: -0.1700
Data Index: 6091626 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1664. Min Range: -6.1664
Max Act: 5.6976. Min Act: -0.1700
Data Index: 2642334 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1664. Min Range: -6.1664
Max Act: 5.6976. Min Act: -0.1700
Data Index: 1611629 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1664. Min Range: -6.1664
Max Act: 5.6664. Min Act: -0.1700
Data Index: 6894662 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1664. Min Range: -6.1664
Max Act: 5.6664. Min Act: -0.1700
Data Index: 7736114 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1664. Min Range: -6.1664
Max Act: 5.6664. Min Act: -0.1700
Data Index: 7576691 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1664. Min Range: -6.1664
Max Act: 5.6351. Min Act: -0.1700
Data Index: 6559533 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1664. Min Range: -6.1664
Max Act: 5.6664. Min Act: -0.1700
Data Index: 5058853 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1664. Min Range: -6.1664
Max Act: 5.6039. Min Act: -0.1700
Data Index: 2450837 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1664. Min Range: -6.1664
Max Act: 5.6351. Min Act: -0.1700
Data Index: 453999 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1664. Min Range: -6.1664
Max Act: 5.6351. Min Act: -0.1700
Data Index: 1801599 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1664. Min Range: -6.1664
Max Act: 5.6351. Min Act: -0.1700
Data Index: 4965720 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1664. Min Range: -6.1664
Max Act: 5.6351. Min Act: -0.1700
Data Index: 306958 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1664. Min Range: -6.1664
Max Act: 5.6351. Min Act: -0.1700
Data Index: 391528 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19