Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 611 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3336. Min Range: -6.3336
Max Act: 6.3336. Min Act: -0.1700
Data Index: 516427 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3336. Min Range: -6.3336
Max Act: 6.2711. Min Act: -0.1700
Data Index: 7080797 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3336. Min Range: -6.3336
Max Act: 6.2399. Min Act: -0.1700
Data Index: 3948987 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3336. Min Range: -6.3336
Max Act: 6.1774. Min Act: -0.1700
Data Index: 6731916 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3336. Min Range: -6.3336
Max Act: 6.1774. Min Act: -0.1700
Data Index: 4076167 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3336. Min Range: -6.3336
Max Act: 6.1461. Min Act: -0.1700
Data Index: 8444267 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3336. Min Range: -6.3336
Max Act: 6.0836. Min Act: -0.1700
Data Index: 991350 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3336. Min Range: -6.3336
Max Act: 6.1149. Min Act: -0.1700
Data Index: 8489589 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3336. Min Range: -6.3336
Max Act: 6.0836. Min Act: -0.1700
Data Index: 7996338 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3336. Min Range: -6.3336
Max Act: 6.0524. Min Act: -0.1700
Data Index: 5363528 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3336. Min Range: -6.3336
Max Act: 6.0836. Min Act: -0.1700
Data Index: 5191327 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3336. Min Range: -6.3336
Max Act: 6.0524. Min Act: -0.1700
Data Index: 1310047 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3336. Min Range: -6.3336
Max Act: 6.0211. Min Act: -0.1700
Data Index: 8516522 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3336. Min Range: -6.3336
Max Act: 6.0524. Min Act: -0.1700
Data Index: 3745227 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3336. Min Range: -6.3336
Max Act: 6.0836. Min Act: -0.1700
Data Index: 5792191 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3336. Min Range: -6.3336
Max Act: 6.0524. Min Act: -0.1700
Data Index: 2126592 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3336. Min Range: -6.3336
Max Act: 6.0211. Min Act: -0.1700
Data Index: 4572437 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3336. Min Range: -6.3336
Max Act: 5.9899. Min Act: -0.1700
Data Index: 1103916 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3336. Min Range: -6.3336
Max Act: 6.0211. Min Act: -0.1700
Data Index: 1195636 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3336. Min Range: -6.3336
Max Act: 6.0211. Min Act: -0.1700
Data Index: 3154470 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19