Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1185. Min Range: -5.1185
Max Act: 5.1185. Min Act: -0.1700
Data Index: 3246391 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1185. Min Range: -5.1185
Max Act: 5.0560. Min Act: -0.1700
Data Index: 6105999 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.8998. Min Act: -0.1700
Data Index: 7228427 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.8998. Min Act: -0.1700
Data Index: 8737791 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.8998. Min Act: -0.1700
Data Index: 4056488 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.8685. Min Act: -0.1700
Data Index: 1799993 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.8373. Min Act: -0.1700
Data Index: 8706562 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.8060. Min Act: -0.1700
Data Index: 4061859 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.7435. Min Act: -0.1700
Data Index: 2239911 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.7123. Min Act: -0.1700
Data Index: 4858689 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.6498. Min Act: -0.1700
Data Index: 132591 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.6498. Min Act: -0.1700
Data Index: 4573393 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.6185. Min Act: -0.1700
Data Index: 8299680 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.6185. Min Act: -0.1700
Data Index: 2736760 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.5560. Min Act: -0.1700
Data Index: 8589769 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.5560. Min Act: -0.1700
Data Index: 6989039 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.5248. Min Act: -0.1700
Data Index: 3311325 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.5248. Min Act: -0.1700
Data Index: 7228426 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.5248. Min Act: -0.1700
Data Index: 272552 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.5248. Min Act: -0.1700
Data Index: 2749592 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19