Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5171 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6508. Min Range: -7.6508
Max Act: 7.6508. Min Act: -0.1700
Data Index: 179982 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6508. Min Range: -7.6508
Max Act: 7.3071. Min Act: -0.1700
Data Index: 1995229 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6508. Min Range: -7.6508
Max Act: 7.3071. Min Act: -0.1700
Data Index: 589333 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6508. Min Range: -7.6508
Max Act: 7.1821. Min Act: -0.1700
Data Index: 5412070 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6508. Min Range: -7.6508
Max Act: 7.1821. Min Act: -0.1700
Data Index: 6964778 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6508. Min Range: -7.6508
Max Act: 7.1508. Min Act: -0.1700
Data Index: 5442555 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6508. Min Range: -7.6508
Max Act: 7.0883. Min Act: -0.1700
Data Index: 4900700 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6508. Min Range: -7.6508
Max Act: 7.1196. Min Act: -0.1700
Data Index: 6193628 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6508. Min Range: -7.6508
Max Act: 7.1196. Min Act: -0.1700
Data Index: 1270005 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6508. Min Range: -7.6508
Max Act: 7.0258. Min Act: -0.1700
Data Index: 4917923 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6508. Min Range: -7.6508
Max Act: 6.9321. Min Act: -0.1700
Data Index: 5223414 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6508. Min Range: -7.6508
Max Act: 6.9633. Min Act: -0.1700
Data Index: 5079855 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6508. Min Range: -7.6508
Max Act: 6.9321. Min Act: -0.1700
Data Index: 8527177 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6508. Min Range: -7.6508
Max Act: 6.9633. Min Act: -0.1700
Data Index: 3121435 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6508. Min Range: -7.6508
Max Act: 6.9633. Min Act: -0.1700
Data Index: 6214389 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6508. Min Range: -7.6508
Max Act: 6.9321. Min Act: -0.1700
Data Index: 3005424 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6508. Min Range: -7.6508
Max Act: 6.9008. Min Act: -0.1700
Data Index: 458092 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6508. Min Range: -7.6508
Max Act: 6.8696. Min Act: -0.1700
Data Index: 7342740 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6508. Min Range: -7.6508
Max Act: 6.8696. Min Act: -0.1700
Data Index: 3153445 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6508. Min Range: -7.6508
Max Act: 6.8696. Min Act: -0.1700
Data Index: 7464276 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19