Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2335 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.6397. Min Act: -0.1700
Data Index: 64720 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.5772. Min Act: -0.1700
Data Index: 7054124 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.5459. Min Act: -0.1700
Data Index: 5045482 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.5147. Min Act: -0.1700
Data Index: 1844666 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.4834. Min Act: -0.1700
Data Index: 5249116 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.4834. Min Act: -0.1700
Data Index: 8367728 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.4522. Min Act: -0.1700
Data Index: 5651568 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.4522. Min Act: -0.1700
Data Index: 4556457 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.4522. Min Act: -0.1700
Data Index: 4328562 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.4209. Min Act: -0.1700
Data Index: 7161872 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.4522. Min Act: -0.1700
Data Index: 6566378 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.4522. Min Act: -0.1700
Data Index: 6300482 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.4522. Min Act: -0.1700
Data Index: 8804075 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.4209. Min Act: -0.1700
Data Index: 4049113 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.4522. Min Act: -0.1700
Data Index: 3595031 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.4209. Min Act: -0.1700
Data Index: 8232561 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.3897. Min Act: -0.1700
Data Index: 8069959 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.4209. Min Act: -0.1700
Data Index: 2471009 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.3897. Min Act: -0.1700
Data Index: 3083550 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6397. Min Range: -4.6397
Max Act: 4.4209. Min Act: -0.1700
Data Index: 7588931 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19