Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3515 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2753. Min Range: -7.2753
Max Act: 7.2753. Min Act: -0.1700
Data Index: 7991451 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2753. Min Range: -7.2753
Max Act: 6.8378. Min Act: -0.1700
Data Index: 395475 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2753. Min Range: -7.2753
Max Act: 6.8066. Min Act: -0.1700
Data Index: 6641723 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2753. Min Range: -7.2753
Max Act: 6.8066. Min Act: -0.1700
Data Index: 1139187 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2753. Min Range: -7.2753
Max Act: 6.8066. Min Act: -0.1700
Data Index: 6054952 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2753. Min Range: -7.2753
Max Act: 6.7441. Min Act: -0.1700
Data Index: 1497892 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2753. Min Range: -7.2753
Max Act: 6.7441. Min Act: -0.1700
Data Index: 318011 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2753. Min Range: -7.2753
Max Act: 6.7128. Min Act: -0.1700
Data Index: 4635888 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2753. Min Range: -7.2753
Max Act: 6.6503. Min Act: -0.1700
Data Index: 1221188 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2753. Min Range: -7.2753
Max Act: 6.6503. Min Act: -0.1700
Data Index: 6671788 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2753. Min Range: -7.2753
Max Act: 6.6503. Min Act: -0.1700
Data Index: 1132531 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2753. Min Range: -7.2753
Max Act: 6.5878. Min Act: -0.1700
Data Index: 7194813 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2753. Min Range: -7.2753
Max Act: 6.5878. Min Act: -0.1700
Data Index: 230090 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2753. Min Range: -7.2753
Max Act: 6.5253. Min Act: -0.1700
Data Index: 8565426 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2753. Min Range: -7.2753
Max Act: 6.5566. Min Act: -0.1700
Data Index: 557810 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2753. Min Range: -7.2753
Max Act: 6.5566. Min Act: -0.1700
Data Index: 2238602 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2753. Min Range: -7.2753
Max Act: 6.5253. Min Act: -0.1700
Data Index: 3547935 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2753. Min Range: -7.2753
Max Act: 6.4941. Min Act: -0.1700
Data Index: 1399610 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2753. Min Range: -7.2753
Max Act: 6.4941. Min Act: -0.1700
Data Index: 8489648 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2753. Min Range: -7.2753
Max Act: 6.4316. Min Act: -0.1700
Data Index: 6346304 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19