Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1796 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.7309. Min Act: -0.1700
Data Index: 2531148 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.6371. Min Act: -0.1700
Data Index: 8274931 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.6059. Min Act: -0.1700
Data Index: 4586721 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.5121. Min Act: -0.1700
Data Index: 6366069 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.4809. Min Act: -0.1700
Data Index: 7845684 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.4809. Min Act: -0.1700
Data Index: 4152420 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.4809. Min Act: -0.1700
Data Index: 1202644 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.4496. Min Act: -0.1700
Data Index: 4084010 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.4184. Min Act: -0.1700
Data Index: 5146125 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.3871. Min Act: -0.1700
Data Index: 6178894 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.3871. Min Act: -0.1700
Data Index: 1242261 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.3246. Min Act: -0.1700
Data Index: 915904 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.3246. Min Act: -0.1700
Data Index: 5634543 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.2621. Min Act: -0.1700
Data Index: 2153311 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.2621. Min Act: -0.1700
Data Index: 8794759 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.2621. Min Act: -0.1700
Data Index: 5867858 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.2309. Min Act: -0.1700
Data Index: 4606423 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.2309. Min Act: -0.1700
Data Index: 6361371 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.2309. Min Act: -0.1700
Data Index: 4945993 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7309. Min Range: -6.7309
Max Act: 6.1996. Min Act: -0.1700
Data Index: 4680653 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19