Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2745 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1117. Min Range: -8.1117
Max Act: 8.1117. Min Act: -0.1700
Data Index: 54229 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1117. Min Range: -8.1117
Max Act: 7.7992. Min Act: -0.1700
Data Index: 5450251 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1117. Min Range: -8.1117
Max Act: 7.7367. Min Act: -0.1700
Data Index: 2087042 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1117. Min Range: -8.1117
Max Act: 7.7367. Min Act: -0.1700
Data Index: 6824549 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1117. Min Range: -8.1117
Max Act: 7.6742. Min Act: -0.1700
Data Index: 4554956 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1117. Min Range: -8.1117
Max Act: 7.6742. Min Act: -0.1700
Data Index: 1254374 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1117. Min Range: -8.1117
Max Act: 7.6117. Min Act: -0.1700
Data Index: 5799709 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1117. Min Range: -8.1117
Max Act: 7.6117. Min Act: -0.1700
Data Index: 255697 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1117. Min Range: -8.1117
Max Act: 7.6117. Min Act: -0.1700
Data Index: 8816038 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1117. Min Range: -8.1117
Max Act: 7.5492. Min Act: -0.1700
Data Index: 8147351 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1117. Min Range: -8.1117
Max Act: 7.5179. Min Act: -0.1700
Data Index: 6987542 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1117. Min Range: -8.1117
Max Act: 7.4867. Min Act: -0.1700
Data Index: 1863924 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1117. Min Range: -8.1117
Max Act: 7.4554. Min Act: -0.1700
Data Index: 2830767 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1117. Min Range: -8.1117
Max Act: 7.4242. Min Act: -0.1700
Data Index: 2828148 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1117. Min Range: -8.1117
Max Act: 7.4242. Min Act: -0.1700
Data Index: 684657 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1117. Min Range: -8.1117
Max Act: 7.4554. Min Act: -0.1700
Data Index: 4061731 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1117. Min Range: -8.1117
Max Act: 7.3929. Min Act: -0.1700
Data Index: 7717993 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1117. Min Range: -8.1117
Max Act: 7.3304. Min Act: -0.1700
Data Index: 880819 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1117. Min Range: -8.1117
Max Act: 7.3617. Min Act: -0.1700
Data Index: 3771512 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1117. Min Range: -8.1117
Max Act: 7.3304. Min Act: -0.1700
Data Index: 3113523 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19