Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4656 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1451. Min Range: -6.1451
Max Act: 6.1451. Min Act: -0.1700
Data Index: 1891375 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1451. Min Range: -6.1451
Max Act: 5.9263. Min Act: -0.1700
Data Index: 8263090 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1451. Min Range: -6.1451
Max Act: 5.8638. Min Act: -0.1700
Data Index: 7076810 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1451. Min Range: -6.1451
Max Act: 5.7701. Min Act: -0.1700
Data Index: 3853041 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1451. Min Range: -6.1451
Max Act: 5.8013. Min Act: -0.1700
Data Index: 1299008 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1451. Min Range: -6.1451
Max Act: 5.7076. Min Act: -0.1700
Data Index: 5733223 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1451. Min Range: -6.1451
Max Act: 5.6763. Min Act: -0.1700
Data Index: 8225411 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1451. Min Range: -6.1451
Max Act: 5.7076. Min Act: -0.1700
Data Index: 5861083 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1451. Min Range: -6.1451
Max Act: 5.6451. Min Act: -0.1700
Data Index: 1767349 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1451. Min Range: -6.1451
Max Act: 5.6451. Min Act: -0.1700
Data Index: 6445847 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1451. Min Range: -6.1451
Max Act: 5.6451. Min Act: -0.1700
Data Index: 153504 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1451. Min Range: -6.1451
Max Act: 5.6138. Min Act: -0.1700
Data Index: 4112257 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1451. Min Range: -6.1451
Max Act: 5.6138. Min Act: -0.1700
Data Index: 7657639 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1451. Min Range: -6.1451
Max Act: 5.6138. Min Act: -0.1700
Data Index: 4628642 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1451. Min Range: -6.1451
Max Act: 5.6138. Min Act: -0.1700
Data Index: 7806855 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1451. Min Range: -6.1451
Max Act: 5.6138. Min Act: -0.1700
Data Index: 1099636 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1451. Min Range: -6.1451
Max Act: 5.5826. Min Act: -0.1700
Data Index: 382837 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1451. Min Range: -6.1451
Max Act: 5.5826. Min Act: -0.1700
Data Index: 4508410 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1451. Min Range: -6.1451
Max Act: 5.5826. Min Act: -0.1700
Data Index: 4654501 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1451. Min Range: -6.1451
Max Act: 5.5513. Min Act: -0.1700
Data Index: 1480346 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19