Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1422 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.7866. Min Act: -0.1700
Data Index: 4605940 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.7241. Min Act: -0.1700
Data Index: 1163215 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.7241. Min Act: -0.1700
Data Index: 3493044 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.5679. Min Act: -0.1700
Data Index: 3081788 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.5366. Min Act: -0.1700
Data Index: 8100368 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.4429. Min Act: -0.1700
Data Index: 625581 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.4116. Min Act: -0.1700
Data Index: 2533230 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.3804. Min Act: -0.1700
Data Index: 1480289 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.3491. Min Act: -0.1700
Data Index: 4958333 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.3179. Min Act: -0.1700
Data Index: 7807681 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.3179. Min Act: -0.1700
Data Index: 598089 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.2554. Min Act: -0.1700
Data Index: 169081 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.2241. Min Act: -0.1700
Data Index: 32915 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.2554. Min Act: -0.1700
Data Index: 882655 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.2241. Min Act: -0.1700
Data Index: 2988281 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.2554. Min Act: -0.1700
Data Index: 7195431 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.1929. Min Act: -0.1700
Data Index: 3380578 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.2241. Min Act: -0.1700
Data Index: 2748696 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.1616. Min Act: -0.1700
Data Index: 7319524 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7866. Min Range: -6.7866
Max Act: 6.2241. Min Act: -0.1700
Data Index: 3987120 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19