Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3693 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5372. Min Range: -7.5372
Max Act: 7.5372. Min Act: -0.1700
Data Index: 6653838 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5372. Min Range: -7.5372
Max Act: 7.2872. Min Act: -0.1700
Data Index: 6021856 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5372. Min Range: -7.5372
Max Act: 7.1935. Min Act: -0.1700
Data Index: 7450734 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5372. Min Range: -7.5372
Max Act: 7.1310. Min Act: -0.1700
Data Index: 2921705 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5372. Min Range: -7.5372
Max Act: 7.1310. Min Act: -0.1700
Data Index: 5783157 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5372. Min Range: -7.5372
Max Act: 7.1310. Min Act: -0.1700
Data Index: 3895706 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5372. Min Range: -7.5372
Max Act: 6.9747. Min Act: -0.1700
Data Index: 4839982 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5372. Min Range: -7.5372
Max Act: 6.9747. Min Act: -0.1700
Data Index: 7189399 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5372. Min Range: -7.5372
Max Act: 6.9435. Min Act: -0.1700
Data Index: 437829 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5372. Min Range: -7.5372
Max Act: 6.9435. Min Act: -0.1700
Data Index: 3735497 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5372. Min Range: -7.5372
Max Act: 6.9435. Min Act: -0.1700
Data Index: 1788949 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5372. Min Range: -7.5372
Max Act: 6.9122. Min Act: -0.1700
Data Index: 6318362 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5372. Min Range: -7.5372
Max Act: 6.8810. Min Act: -0.1700
Data Index: 8694953 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5372. Min Range: -7.5372
Max Act: 6.8810. Min Act: -0.1700
Data Index: 7120792 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5372. Min Range: -7.5372
Max Act: 6.8810. Min Act: -0.1700
Data Index: 3998839 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5372. Min Range: -7.5372
Max Act: 6.8810. Min Act: -0.1700
Data Index: 1767981 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5372. Min Range: -7.5372
Max Act: 6.8497. Min Act: -0.1700
Data Index: 5414556 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5372. Min Range: -7.5372
Max Act: 6.8810. Min Act: -0.1700
Data Index: 3004318 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5372. Min Range: -7.5372
Max Act: 6.8497. Min Act: -0.1700
Data Index: 5712621 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5372. Min Range: -7.5372
Max Act: 6.8185. Min Act: -0.1700
Data Index: 4313582 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19