Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2822 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1173. Min Range: -7.1173
Max Act: 7.1173. Min Act: -0.1700
Data Index: 7798467 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1173. Min Range: -7.1173
Max Act: 7.0235. Min Act: -0.1700
Data Index: 1411227 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1173. Min Range: -7.1173
Max Act: 6.9610. Min Act: -0.1700
Data Index: 1546930 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1173. Min Range: -7.1173
Max Act: 6.9610. Min Act: -0.1700
Data Index: 7547605 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1173. Min Range: -7.1173
Max Act: 6.8985. Min Act: -0.1700
Data Index: 5905859 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1173. Min Range: -7.1173
Max Act: 6.8360. Min Act: -0.1700
Data Index: 6457390 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1173. Min Range: -7.1173
Max Act: 6.8048. Min Act: -0.1700
Data Index: 5304914 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1173. Min Range: -7.1173
Max Act: 6.8360. Min Act: -0.1700
Data Index: 3580468 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1173. Min Range: -7.1173
Max Act: 6.8048. Min Act: -0.1700
Data Index: 1291220 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1173. Min Range: -7.1173
Max Act: 6.8048. Min Act: -0.1700
Data Index: 6517598 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1173. Min Range: -7.1173
Max Act: 6.8360. Min Act: -0.1700
Data Index: 7861793 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1173. Min Range: -7.1173
Max Act: 6.7735. Min Act: -0.1700
Data Index: 1218417 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1173. Min Range: -7.1173
Max Act: 6.7735. Min Act: -0.1700
Data Index: 303891 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1173. Min Range: -7.1173
Max Act: 6.7423. Min Act: -0.1700
Data Index: 1793076 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1173. Min Range: -7.1173
Max Act: 6.7423. Min Act: -0.1700
Data Index: 4584 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1173. Min Range: -7.1173
Max Act: 6.7423. Min Act: -0.1700
Data Index: 7959336 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1173. Min Range: -7.1173
Max Act: 6.6798. Min Act: -0.1700
Data Index: 1898527 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1173. Min Range: -7.1173
Max Act: 6.7110. Min Act: -0.1700
Data Index: 2693684 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1173. Min Range: -7.1173
Max Act: 6.7110. Min Act: -0.1700
Data Index: 6719314 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1173. Min Range: -7.1173
Max Act: 6.7110. Min Act: -0.1700
Data Index: 1344024 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19