Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3120 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.2852. Min Act: -0.1700
Data Index: 4329703 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.2539. Min Act: -0.1700
Data Index: 6801948 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.2539. Min Act: -0.1700
Data Index: 2223435 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.1914. Min Act: -0.1700
Data Index: 5442781 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.1914. Min Act: -0.1700
Data Index: 6916375 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.1602. Min Act: -0.1700
Data Index: 7998116 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.1289. Min Act: -0.1700
Data Index: 3200591 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.1289. Min Act: -0.1700
Data Index: 2197215 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.1289. Min Act: -0.1700
Data Index: 8661051 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.1289. Min Act: -0.1700
Data Index: 6882266 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.1289. Min Act: -0.1700
Data Index: 1262093 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.1289. Min Act: -0.1700
Data Index: 4890888 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.1289. Min Act: -0.1700
Data Index: 43925 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.0977. Min Act: -0.1700
Data Index: 526280 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.0977. Min Act: -0.1700
Data Index: 3293996 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.0977. Min Act: -0.1700
Data Index: 4959540 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.0977. Min Act: -0.1700
Data Index: 1552480 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.0977. Min Act: -0.1700
Data Index: 7968977 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.0977. Min Act: -0.1700
Data Index: 1626658 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.0977. Min Act: -0.1700
Data Index: 6166259 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19