Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2919 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2243. Min Range: -6.2243
Max Act: 6.2243. Min Act: -0.1700
Data Index: 4059593 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2243. Min Range: -6.2243
Max Act: 6.1618. Min Act: -0.1700
Data Index: 1260629 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2243. Min Range: -6.2243
Max Act: 6.1306. Min Act: -0.1700
Data Index: 5346307 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2243. Min Range: -6.2243
Max Act: 6.1306. Min Act: -0.1700
Data Index: 8808022 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2243. Min Range: -6.2243
Max Act: 6.0681. Min Act: -0.1700
Data Index: 1643906 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2243. Min Range: -6.2243
Max Act: 6.0368. Min Act: -0.1700
Data Index: 5840163 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2243. Min Range: -6.2243
Max Act: 6.0368. Min Act: -0.1700
Data Index: 4984797 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2243. Min Range: -6.2243
Max Act: 6.0056. Min Act: -0.1700
Data Index: 1482996 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2243. Min Range: -6.2243
Max Act: 6.0056. Min Act: -0.1700
Data Index: 8710509 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2243. Min Range: -6.2243
Max Act: 6.0056. Min Act: -0.1700
Data Index: 5549825 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2243. Min Range: -6.2243
Max Act: 5.9431. Min Act: -0.1700
Data Index: 455866 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2243. Min Range: -6.2243
Max Act: 5.9743. Min Act: -0.1700
Data Index: 7461540 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2243. Min Range: -6.2243
Max Act: 5.9431. Min Act: -0.1700
Data Index: 8090004 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2243. Min Range: -6.2243
Max Act: 5.9431. Min Act: -0.1700
Data Index: 2590808 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2243. Min Range: -6.2243
Max Act: 5.9431. Min Act: -0.1700
Data Index: 5589338 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2243. Min Range: -6.2243
Max Act: 5.9118. Min Act: -0.1700
Data Index: 4943001 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2243. Min Range: -6.2243
Max Act: 5.9431. Min Act: -0.1700
Data Index: 7558026 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2243. Min Range: -6.2243
Max Act: 5.8806. Min Act: -0.1700
Data Index: 6739333 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2243. Min Range: -6.2243
Max Act: 5.8806. Min Act: -0.1700
Data Index: 6620573 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2243. Min Range: -6.2243
Max Act: 5.8806. Min Act: -0.1700
Data Index: 5141750 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19