Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3435 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2771. Min Range: -7.2771
Max Act: 7.2771. Min Act: -0.1700
Data Index: 3430872 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2771. Min Range: -7.2771
Max Act: 7.2771. Min Act: -0.1700
Data Index: 5442241 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2771. Min Range: -7.2771
Max Act: 7.1833. Min Act: -0.1700
Data Index: 5002896 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2771. Min Range: -7.2771
Max Act: 7.1521. Min Act: -0.1700
Data Index: 4282664 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2771. Min Range: -7.2771
Max Act: 7.0583. Min Act: -0.1700
Data Index: 3453131 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.9958. Min Act: -0.1700
Data Index: 1169009 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.9958. Min Act: -0.1700
Data Index: 2639342 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.9333. Min Act: -0.1700
Data Index: 7532843 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.9646. Min Act: -0.1700
Data Index: 5670664 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.9333. Min Act: -0.1700
Data Index: 5485415 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.9021. Min Act: -0.1700
Data Index: 5680928 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.9333. Min Act: -0.1700
Data Index: 4689609 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.8708. Min Act: -0.1700
Data Index: 1973990 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.8396. Min Act: -0.1700
Data Index: 8527209 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.8708. Min Act: -0.1700
Data Index: 6010125 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.8083. Min Act: -0.1700
Data Index: 3003319 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.8396. Min Act: -0.1700
Data Index: 4093486 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.8708. Min Act: -0.1700
Data Index: 5680929 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.8396. Min Act: -0.1700
Data Index: 644014 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.8083. Min Act: -0.1700
Data Index: 4898843 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19