Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 778 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.7248. Min Act: -0.1700
Data Index: 378096 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.7421. Min Act: -0.1700
Data Index: 3286107 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.7075. Min Act: -0.1700
Data Index: 4542271 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.7075. Min Act: -0.1700
Data Index: 2522366 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.6728. Min Act: -0.1700
Data Index: 5133336 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.6728. Min Act: -0.1700
Data Index: 5817595 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.6554. Min Act: -0.1700
Data Index: 8143383 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.6554. Min Act: -0.1700
Data Index: 5816345 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.6554. Min Act: -0.1700
Data Index: 1986631 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.6380. Min Act: -0.1700
Data Index: 7249485 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.6380. Min Act: -0.1700
Data Index: 8401630 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.6205. Min Act: -0.1700
Data Index: 7356746 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.6554. Min Act: -0.1700
Data Index: 172395 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.6031. Min Act: -0.1700
Data Index: 5222602 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.6205. Min Act: -0.1700
Data Index: 1850822 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.5681. Min Act: -0.1700
Data Index: 4235261 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.6031. Min Act: -0.1700
Data Index: 8356296 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.5856. Min Act: -0.1700
Data Index: 1390719 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.6205. Min Act: -0.1700
Data Index: 2289523 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7421. Min Range: -1.7421
Max Act: 1.5681. Min Act: -0.1700
Data Index: 6694715 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19