Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1863 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2900. Min Range: -4.2900
Max Act: 4.2900. Min Act: -0.1700
Data Index: 7758772 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2900. Min Range: -4.2900
Max Act: 4.1650. Min Act: -0.1700
Data Index: 7562680 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2900. Min Range: -4.2900
Max Act: 4.0399. Min Act: -0.1700
Data Index: 2542692 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2900. Min Range: -4.2900
Max Act: 4.0087. Min Act: -0.1700
Data Index: 5706742 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2900. Min Range: -4.2900
Max Act: 4.0087. Min Act: -0.1700
Data Index: 8797829 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.9618. Min Act: -0.1700
Data Index: 1366879 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.9618. Min Act: -0.1700
Data Index: 3911893 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.9462. Min Act: -0.1700
Data Index: 143048 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2900. Min Range: -4.2900
Max Act: 4.0087. Min Act: -0.1700
Data Index: 4068469 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.7585. Min Act: -0.1700
Data Index: 6493335 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.9149. Min Act: -0.1700
Data Index: 3692671 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.8524. Min Act: -0.1700
Data Index: 3583796 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.8836. Min Act: -0.1700
Data Index: 5459837 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.8680. Min Act: -0.1700
Data Index: 944136 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.8680. Min Act: -0.1700
Data Index: 4486930 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.8993. Min Act: -0.1700
Data Index: 3732594 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.8367. Min Act: -0.1700
Data Index: 7402835 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.8993. Min Act: -0.1700
Data Index: 2314402 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.7898. Min Act: -0.1700
Data Index: 7247458 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2900. Min Range: -4.2900
Max Act: 3.7898. Min Act: -0.1700
Data Index: 3145019 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19