Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3626 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5168. Min Range: -9.5168
Max Act: 9.5168. Min Act: -0.1700
Data Index: 6516350 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5168. Min Range: -9.5168
Max Act: 9.1418. Min Act: -0.1700
Data Index: 7131058 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5168. Min Range: -9.5168
Max Act: 9.0793. Min Act: -0.1700
Data Index: 2911441 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5168. Min Range: -9.5168
Max Act: 9.0793. Min Act: -0.1700
Data Index: 5054958 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5168. Min Range: -9.5168
Max Act: 9.0793. Min Act: -0.1700
Data Index: 6898164 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5168. Min Range: -9.5168
Max Act: 9.0168. Min Act: -0.1700
Data Index: 601078 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5168. Min Range: -9.5168
Max Act: 9.0168. Min Act: -0.1700
Data Index: 622915 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5168. Min Range: -9.5168
Max Act: 8.9543. Min Act: -0.1700
Data Index: 6418616 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5168. Min Range: -9.5168
Max Act: 8.8918. Min Act: -0.1700
Data Index: 8625091 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5168. Min Range: -9.5168
Max Act: 8.8918. Min Act: -0.1700
Data Index: 6155232 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5168. Min Range: -9.5168
Max Act: 8.8918. Min Act: -0.1700
Data Index: 2920008 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5168. Min Range: -9.5168
Max Act: 8.8293. Min Act: -0.1700
Data Index: 4107887 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5168. Min Range: -9.5168
Max Act: 8.8293. Min Act: -0.1700
Data Index: 7049138 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5168. Min Range: -9.5168
Max Act: 8.8293. Min Act: -0.1700
Data Index: 5414224 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5168. Min Range: -9.5168
Max Act: 8.8293. Min Act: -0.1700
Data Index: 211068 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5168. Min Range: -9.5168
Max Act: 8.8293. Min Act: -0.1700
Data Index: 8795651 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5168. Min Range: -9.5168
Max Act: 8.8293. Min Act: -0.1700
Data Index: 6109496 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5168. Min Range: -9.5168
Max Act: 8.8293. Min Act: -0.1700
Data Index: 4665487 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5168. Min Range: -9.5168
Max Act: 8.7668. Min Act: -0.1700
Data Index: 6984033 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5168. Min Range: -9.5168
Max Act: 8.7668. Min Act: -0.1700
Data Index: 8426867 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19