Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2103 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.8403. Min Act: -0.1700
Data Index: 5649185 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.8246. Min Act: -0.1700
Data Index: 3907226 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.7777. Min Act: -0.1700
Data Index: 8742782 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.7777. Min Act: -0.1700
Data Index: 7947131 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.8090. Min Act: -0.1700
Data Index: 5308623 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.7464. Min Act: -0.1700
Data Index: 5040678 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.7151. Min Act: -0.1700
Data Index: 3485589 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.7151. Min Act: -0.1700
Data Index: 671146 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.6839. Min Act: -0.1700
Data Index: 3871803 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.6682. Min Act: -0.1700
Data Index: 6139231 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.6526. Min Act: -0.1700
Data Index: 3406361 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.6369. Min Act: -0.1700
Data Index: 313436 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.6213. Min Act: -0.1700
Data Index: 1079091 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.6213. Min Act: -0.1700
Data Index: 3389161 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.6369. Min Act: -0.1700
Data Index: 5632148 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.6213. Min Act: -0.1700
Data Index: 162608 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.5900. Min Act: -0.1700
Data Index: 687407 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.5900. Min Act: -0.1700
Data Index: 6344975 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.5900. Min Act: -0.1700
Data Index: 6182470 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8403. Min Range: -3.8403
Max Act: 3.6056. Min Act: -0.1700
Data Index: 3594259 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19