Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5387 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2598. Min Range: -6.2598
Max Act: 6.2598. Min Act: -0.1700
Data Index: 3307956 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2598. Min Range: -6.2598
Max Act: 6.2285. Min Act: -0.1700
Data Index: 1947 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2598. Min Range: -6.2598
Max Act: 5.9473. Min Act: -0.1700
Data Index: 6486021 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2598. Min Range: -6.2598
Max Act: 5.8848. Min Act: -0.1700
Data Index: 3098535 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2598. Min Range: -6.2598
Max Act: 5.8535. Min Act: -0.1700
Data Index: 272175 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2598. Min Range: -6.2598
Max Act: 5.8223. Min Act: -0.1700
Data Index: 6864136 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2598. Min Range: -6.2598
Max Act: 5.8223. Min Act: -0.1700
Data Index: 3941548 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2598. Min Range: -6.2598
Max Act: 5.8223. Min Act: -0.1700
Data Index: 1119047 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2598. Min Range: -6.2598
Max Act: 5.7910. Min Act: -0.1700
Data Index: 3233188 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2598. Min Range: -6.2598
Max Act: 5.7285. Min Act: -0.1700
Data Index: 7078937 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2598. Min Range: -6.2598
Max Act: 5.7285. Min Act: -0.1700
Data Index: 1314854 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2598. Min Range: -6.2598
Max Act: 5.7285. Min Act: -0.1700
Data Index: 7548966 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2598. Min Range: -6.2598
Max Act: 5.7285. Min Act: -0.1700
Data Index: 4544590 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2598. Min Range: -6.2598
Max Act: 5.6973. Min Act: -0.1700
Data Index: 2765279 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2598. Min Range: -6.2598
Max Act: 5.7285. Min Act: -0.1700
Data Index: 5441085 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2598. Min Range: -6.2598
Max Act: 5.6973. Min Act: -0.1700
Data Index: 2905833 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2598. Min Range: -6.2598
Max Act: 5.6660. Min Act: -0.1700
Data Index: 5349045 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2598. Min Range: -6.2598
Max Act: 5.6973. Min Act: -0.1700
Data Index: 3455215 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2598. Min Range: -6.2598
Max Act: 5.6660. Min Act: -0.1700
Data Index: 2036538 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2598. Min Range: -6.2598
Max Act: 5.6660. Min Act: -0.1700
Data Index: 4625867 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19