Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5826 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.6781. Min Act: -0.1700
Data Index: 1319816 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.6469. Min Act: -0.1700
Data Index: 2051682 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.6156. Min Act: -0.1700
Data Index: 2881616 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.5844. Min Act: -0.1700
Data Index: 2747645 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.5844. Min Act: -0.1700
Data Index: 8094853 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.5844. Min Act: -0.1700
Data Index: 1224126 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.5219. Min Act: -0.1700
Data Index: 5072342 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.4594. Min Act: -0.1700
Data Index: 8769332 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.4281. Min Act: -0.1700
Data Index: 1915220 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.4594. Min Act: -0.1700
Data Index: 869474 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.4281. Min Act: -0.1700
Data Index: 4759758 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.3969. Min Act: -0.1700
Data Index: 7022481 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.3656. Min Act: -0.1700
Data Index: 1172499 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.3344. Min Act: -0.1700
Data Index: 62795 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.3656. Min Act: -0.1700
Data Index: 8317404 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.3969. Min Act: -0.1700
Data Index: 7682244 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.3344. Min Act: -0.1700
Data Index: 7861531 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.3344. Min Act: -0.1700
Data Index: 3080460 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.3031. Min Act: -0.1700
Data Index: 3696918 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6781. Min Range: -6.6781
Max Act: 6.3031. Min Act: -0.1700
Data Index: 256725 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19