Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4788 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3757. Min Range: -3.3757
Max Act: 3.3757. Min Act: -0.1700
Data Index: 1609645 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3757. Min Range: -3.3757
Max Act: 3.2972. Min Act: -0.1700
Data Index: 8430447 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3757. Min Range: -3.3757
Max Act: 3.1400. Min Act: -0.1700
Data Index: 3631100 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3757. Min Range: -3.3757
Max Act: 3.0454. Min Act: -0.1700
Data Index: 3436559 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3757. Min Range: -3.3757
Max Act: 3.0296. Min Act: -0.1700
Data Index: 3041488 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3757. Min Range: -3.3757
Max Act: 3.0138. Min Act: -0.1700
Data Index: 8059938 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3757. Min Range: -3.3757
Max Act: 3.0138. Min Act: -0.1700
Data Index: 5960889 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3757. Min Range: -3.3757
Max Act: 3.0138. Min Act: -0.1700
Data Index: 2955779 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3757. Min Range: -3.3757
Max Act: 2.9664. Min Act: -0.1700
Data Index: 5414924 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3757. Min Range: -3.3757
Max Act: 2.9822. Min Act: -0.1700
Data Index: 2824453 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3757. Min Range: -3.3757
Max Act: 2.9506. Min Act: -0.1700
Data Index: 4872022 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3757. Min Range: -3.3757
Max Act: 2.9031. Min Act: -0.1700
Data Index: 7901918 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3757. Min Range: -3.3757
Max Act: 2.9031. Min Act: -0.1700
Data Index: 1217835 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3757. Min Range: -3.3757
Max Act: 2.9189. Min Act: -0.1700
Data Index: 6387803 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3757. Min Range: -3.3757
Max Act: 2.9031. Min Act: -0.1700
Data Index: 1121515 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3757. Min Range: -3.3757
Max Act: 2.8872. Min Act: -0.1700
Data Index: 787792 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3757. Min Range: -3.3757
Max Act: 2.8872. Min Act: -0.1700
Data Index: 5027036 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3757. Min Range: -3.3757
Max Act: 2.8872. Min Act: -0.1700
Data Index: 8808559 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3757. Min Range: -3.3757
Max Act: 2.8872. Min Act: -0.1700
Data Index: 5311882 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3757. Min Range: -3.3757
Max Act: 2.8713. Min Act: -0.1700
Data Index: 5830883 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19