Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4061 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2829. Min Range: -6.2829
Max Act: 6.2829. Min Act: -0.1700
Data Index: 30938 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2829. Min Range: -6.2829
Max Act: 6.1892. Min Act: -0.1700
Data Index: 6767546 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2829. Min Range: -6.2829
Max Act: 6.1892. Min Act: -0.1700
Data Index: 5001183 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2829. Min Range: -6.2829
Max Act: 6.1579. Min Act: -0.1700
Data Index: 85885 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2829. Min Range: -6.2829
Max Act: 6.1267. Min Act: -0.1700
Data Index: 3297750 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2829. Min Range: -6.2829
Max Act: 6.0954. Min Act: -0.1700
Data Index: 6259988 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2829. Min Range: -6.2829
Max Act: 6.0329. Min Act: -0.1700
Data Index: 330619 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2829. Min Range: -6.2829
Max Act: 6.0329. Min Act: -0.1700
Data Index: 6797099 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2829. Min Range: -6.2829
Max Act: 6.0017. Min Act: -0.1700
Data Index: 5452183 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2829. Min Range: -6.2829
Max Act: 6.0017. Min Act: -0.1700
Data Index: 8190100 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2829. Min Range: -6.2829
Max Act: 6.0017. Min Act: -0.1700
Data Index: 7183000 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2829. Min Range: -6.2829
Max Act: 5.9704. Min Act: -0.1700
Data Index: 2645092 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2829. Min Range: -6.2829
Max Act: 5.9704. Min Act: -0.1700
Data Index: 2542616 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2829. Min Range: -6.2829
Max Act: 5.9704. Min Act: -0.1700
Data Index: 5666819 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2829. Min Range: -6.2829
Max Act: 5.9704. Min Act: -0.1700
Data Index: 6440202 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2829. Min Range: -6.2829
Max Act: 5.9704. Min Act: -0.1700
Data Index: 527261 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2829. Min Range: -6.2829
Max Act: 5.9704. Min Act: -0.1700
Data Index: 4626456 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2829. Min Range: -6.2829
Max Act: 5.9704. Min Act: -0.1700
Data Index: 996898 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2829. Min Range: -6.2829
Max Act: 5.9392. Min Act: -0.1700
Data Index: 3076402 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2829. Min Range: -6.2829
Max Act: 5.9704. Min Act: -0.1700
Data Index: 7551243 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19