Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4537 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.7694. Min Act: -0.1700
Data Index: 1234634 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.4881. Min Act: -0.1700
Data Index: 1340202 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.4881. Min Act: -0.1700
Data Index: 4515301 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.4256. Min Act: -0.1700
Data Index: 6996140 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.3319. Min Act: -0.1700
Data Index: 5058372 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.3631. Min Act: -0.1700
Data Index: 5072389 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.3006. Min Act: -0.1700
Data Index: 6416504 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.2694. Min Act: -0.1700
Data Index: 7955470 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.2381. Min Act: -0.1700
Data Index: 7447954 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.1756. Min Act: -0.1700
Data Index: 4271337 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.1756. Min Act: -0.1700
Data Index: 1769752 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.1756. Min Act: -0.1700
Data Index: 2768245 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.1756. Min Act: -0.1700
Data Index: 405117 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.1444. Min Act: -0.1700
Data Index: 1744332 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.1444. Min Act: -0.1700
Data Index: 922123 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.1131. Min Act: -0.1700
Data Index: 3115194 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.0819. Min Act: -0.1700
Data Index: 7723677 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.0819. Min Act: -0.1700
Data Index: 3958555 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.0506. Min Act: -0.1700
Data Index: 7094221 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7694. Min Range: -6.7694
Max Act: 6.0506. Min Act: -0.1700
Data Index: 6567825 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19