Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 830 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0753. Min Range: -7.0753
Max Act: 7.0753. Min Act: -0.1700
Data Index: 236168 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0753. Min Range: -7.0753
Max Act: 6.9815. Min Act: -0.1700
Data Index: 1938246 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0753. Min Range: -7.0753
Max Act: 6.9503. Min Act: -0.1700
Data Index: 4716804 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0753. Min Range: -7.0753
Max Act: 6.9190. Min Act: -0.1700
Data Index: 7194348 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0753. Min Range: -7.0753
Max Act: 6.7940. Min Act: -0.1700
Data Index: 4593985 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0753. Min Range: -7.0753
Max Act: 6.7628. Min Act: -0.1700
Data Index: 6147271 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0753. Min Range: -7.0753
Max Act: 6.7628. Min Act: -0.1700
Data Index: 8616078 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0753. Min Range: -7.0753
Max Act: 6.6690. Min Act: -0.1700
Data Index: 2932093 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0753. Min Range: -7.0753
Max Act: 6.6378. Min Act: -0.1700
Data Index: 68009 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0753. Min Range: -7.0753
Max Act: 6.5753. Min Act: -0.1700
Data Index: 5967854 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0753. Min Range: -7.0753
Max Act: 6.5753. Min Act: -0.1700
Data Index: 5441295 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0753. Min Range: -7.0753
Max Act: 6.5128. Min Act: -0.1700
Data Index: 2366294 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0753. Min Range: -7.0753
Max Act: 6.5128. Min Act: -0.1700
Data Index: 7317685 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0753. Min Range: -7.0753
Max Act: 6.5440. Min Act: -0.1700
Data Index: 892634 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0753. Min Range: -7.0753
Max Act: 6.4503. Min Act: -0.1700
Data Index: 644089 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0753. Min Range: -7.0753
Max Act: 6.4503. Min Act: -0.1700
Data Index: 7091531 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0753. Min Range: -7.0753
Max Act: 6.4503. Min Act: -0.1700
Data Index: 5306981 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0753. Min Range: -7.0753
Max Act: 6.4503. Min Act: -0.1700
Data Index: 5343651 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0753. Min Range: -7.0753
Max Act: 6.4190. Min Act: -0.1700
Data Index: 4697707 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0753. Min Range: -7.0753
Max Act: 6.3878. Min Act: -0.1700
Data Index: 5508668 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19