Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2716 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.3257. Min Act: -0.1700
Data Index: 2104749 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.2944. Min Act: -0.1700
Data Index: 5048148 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.2944. Min Act: -0.1700
Data Index: 6278976 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.2319. Min Act: -0.1700
Data Index: 100491 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.2319. Min Act: -0.1700
Data Index: 973413 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.2319. Min Act: -0.1700
Data Index: 3416170 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.2632. Min Act: -0.1700
Data Index: 5035458 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.2319. Min Act: -0.1700
Data Index: 2897509 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.2007. Min Act: -0.1700
Data Index: 4923180 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.1694. Min Act: -0.1700
Data Index: 3261930 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.1694. Min Act: -0.1700
Data Index: 4974134 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.1069. Min Act: -0.1700
Data Index: 1666386 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.1069. Min Act: -0.1700
Data Index: 8688097 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.1069. Min Act: -0.1700
Data Index: 7708494 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.0444. Min Act: -0.1700
Data Index: 5176289 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.0132. Min Act: -0.1700
Data Index: 1494208 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.0132. Min Act: -0.1700
Data Index: 1838305 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3257. Min Range: -6.3257
Max Act: 5.9819. Min Act: -0.1700
Data Index: 1684957 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.0132. Min Act: -0.1700
Data Index: 1060905 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3257. Min Range: -6.3257
Max Act: 5.9819. Min Act: -0.1700
Data Index: 2112792 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19