Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4538. Min Range: -5.4538
Max Act: 5.4538. Min Act: -0.1700
Data Index: 8520121 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4538. Min Range: -5.4538
Max Act: 5.3913. Min Act: -0.1700
Data Index: 8520120 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4538. Min Range: -5.4538
Max Act: 5.0163. Min Act: -0.1700
Data Index: 5981037 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4538. Min Range: -5.4538
Max Act: 5.0163. Min Act: -0.1700
Data Index: 6119710 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4538. Min Range: -5.4538
Max Act: 4.9850. Min Act: -0.1700
Data Index: 7274511 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4538. Min Range: -5.4538
Max Act: 4.9850. Min Act: -0.1700
Data Index: 41897 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4538. Min Range: -5.4538
Max Act: 4.9850. Min Act: -0.1700
Data Index: 1149132 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4538. Min Range: -5.4538
Max Act: 4.9225. Min Act: -0.1700
Data Index: 7274510 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4538. Min Range: -5.4538
Max Act: 4.9538. Min Act: -0.1700
Data Index: 4729253 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4538. Min Range: -5.4538
Max Act: 4.9225. Min Act: -0.1700
Data Index: 6483672 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4538. Min Range: -5.4538
Max Act: 4.9225. Min Act: -0.1700
Data Index: 5813616 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4538. Min Range: -5.4538
Max Act: 4.8913. Min Act: -0.1700
Data Index: 3735588 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4538. Min Range: -5.4538
Max Act: 4.8913. Min Act: -0.1700
Data Index: 1567466 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4538. Min Range: -5.4538
Max Act: 4.8913. Min Act: -0.1700
Data Index: 4221825 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4538. Min Range: -5.4538
Max Act: 4.8913. Min Act: -0.1700
Data Index: 1270474 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4538. Min Range: -5.4538
Max Act: 4.8600. Min Act: -0.1700
Data Index: 2089882 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4538. Min Range: -5.4538
Max Act: 4.8288. Min Act: -0.1700
Data Index: 3579245 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4538. Min Range: -5.4538
Max Act: 4.7975. Min Act: -0.1700
Data Index: 7050412 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4538. Min Range: -5.4538
Max Act: 4.7975. Min Act: -0.1700
Data Index: 3758674 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4538. Min Range: -5.4538
Max Act: 4.7663. Min Act: -0.1700
Data Index: 1049269 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19