Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4355 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.8594. Min Act: -0.1700
Data Index: 7515474 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.7344. Min Act: -0.1700
Data Index: 5729145 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.6719. Min Act: -0.1700
Data Index: 6478522 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.5469. Min Act: -0.1700
Data Index: 8738447 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.5469. Min Act: -0.1700
Data Index: 4821473 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.5156. Min Act: -0.1700
Data Index: 6205355 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.5156. Min Act: -0.1700
Data Index: 5316646 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.5156. Min Act: -0.1700
Data Index: 4602459 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.4844. Min Act: -0.1700
Data Index: 6916398 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.4844. Min Act: -0.1700
Data Index: 7530492 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.4844. Min Act: -0.1700
Data Index: 6297807 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.4531. Min Act: -0.1700
Data Index: 5633386 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.4531. Min Act: -0.1700
Data Index: 6522270 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.4531. Min Act: -0.1700
Data Index: 3917677 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.4219. Min Act: -0.1700
Data Index: 3106888 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.4219. Min Act: -0.1700
Data Index: 7880873 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.4219. Min Act: -0.1700
Data Index: 8648652 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.4219. Min Act: -0.1700
Data Index: 8681241 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.4531. Min Act: -0.1700
Data Index: 2072171 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8594. Min Range: -6.8594
Max Act: 6.4219. Min Act: -0.1700
Data Index: 6388005 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19