Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3376 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.9564. Min Act: -0.1700
Data Index: 3959290 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.9252. Min Act: -0.1700
Data Index: 1256862 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.8627. Min Act: -0.1700
Data Index: 4435185 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.8314. Min Act: -0.1700
Data Index: 6774403 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.8002. Min Act: -0.1700
Data Index: 2444175 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.7689. Min Act: -0.1700
Data Index: 1503230 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.7377. Min Act: -0.1700
Data Index: 7345838 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.6127. Min Act: -0.1700
Data Index: 6957476 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.6127. Min Act: -0.1700
Data Index: 2476325 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.5814. Min Act: -0.1700
Data Index: 8373690 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.5814. Min Act: -0.1700
Data Index: 7978972 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.6127. Min Act: -0.1700
Data Index: 7391782 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.5814. Min Act: -0.1700
Data Index: 3311663 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.5814. Min Act: -0.1700
Data Index: 6225119 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.5814. Min Act: -0.1700
Data Index: 7229011 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.5502. Min Act: -0.1700
Data Index: 3720854 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.5502. Min Act: -0.1700
Data Index: 6785094 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.5502. Min Act: -0.1700
Data Index: 2299625 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.4877. Min Act: -0.1700
Data Index: 2047948 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9564. Min Range: -5.9564
Max Act: 5.5189. Min Act: -0.1700
Data Index: 6785654 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19