Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.8884. Min Act: -0.1700
Data Index: 6799187 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.7634. Min Act: -0.1700
Data Index: 2777406 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.7634. Min Act: -0.1700
Data Index: 6106325 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.7634. Min Act: -0.1700
Data Index: 8149998 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.7322. Min Act: -0.1700
Data Index: 7789662 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.6697. Min Act: -0.1700
Data Index: 7429436 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.7009. Min Act: -0.1700
Data Index: 506937 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.6697. Min Act: -0.1700
Data Index: 7974017 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.6697. Min Act: -0.1700
Data Index: 2435989 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.6697. Min Act: -0.1700
Data Index: 119168 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.6697. Min Act: -0.1700
Data Index: 3225361 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.6384. Min Act: -0.1700
Data Index: 5817194 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.6384. Min Act: -0.1700
Data Index: 6503222 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.6384. Min Act: -0.1700
Data Index: 2831830 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.6072. Min Act: -0.1700
Data Index: 8008021 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.6072. Min Act: -0.1700
Data Index: 5550813 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.6072. Min Act: -0.1700
Data Index: 3111312 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.6072. Min Act: -0.1700
Data Index: 2299331 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.6072. Min Act: -0.1700
Data Index: 2907445 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8884. Min Range: -4.8884
Max Act: 4.6072. Min Act: -0.1700
Data Index: 6743629 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19