Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 457 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2594. Min Range: -6.2594
Max Act: 6.2594. Min Act: -0.1700
Data Index: 7902034 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2594. Min Range: -6.2594
Max Act: 5.8531. Min Act: -0.1700
Data Index: 3409357 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2594. Min Range: -6.2594
Max Act: 5.7906. Min Act: -0.1700
Data Index: 8310139 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2594. Min Range: -6.2594
Max Act: 5.7281. Min Act: -0.1700
Data Index: 5084617 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2594. Min Range: -6.2594
Max Act: 5.6969. Min Act: -0.1700
Data Index: 1262862 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2594. Min Range: -6.2594
Max Act: 5.6031. Min Act: -0.1700
Data Index: 3612919 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2594. Min Range: -6.2594
Max Act: 5.4469. Min Act: -0.1700
Data Index: 1117633 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2594. Min Range: -6.2594
Max Act: 5.4469. Min Act: -0.1700
Data Index: 6466167 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2594. Min Range: -6.2594
Max Act: 5.4469. Min Act: -0.1700
Data Index: 6890729 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2594. Min Range: -6.2594
Max Act: 5.4469. Min Act: -0.1700
Data Index: 5121871 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2594. Min Range: -6.2594
Max Act: 5.4469. Min Act: -0.1700
Data Index: 7870696 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2594. Min Range: -6.2594
Max Act: 5.4469. Min Act: -0.1700
Data Index: 221058 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2594. Min Range: -6.2594
Max Act: 5.3844. Min Act: -0.1700
Data Index: 4657275 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2594. Min Range: -6.2594
Max Act: 5.4156. Min Act: -0.1700
Data Index: 3622180 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2594. Min Range: -6.2594
Max Act: 5.4156. Min Act: -0.1700
Data Index: 1005723 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2594. Min Range: -6.2594
Max Act: 5.4156. Min Act: -0.1700
Data Index: 2748951 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2594. Min Range: -6.2594
Max Act: 5.4156. Min Act: -0.1700
Data Index: 1123289 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2594. Min Range: -6.2594
Max Act: 5.3844. Min Act: -0.1700
Data Index: 1945516 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2594. Min Range: -6.2594
Max Act: 5.4156. Min Act: -0.1700
Data Index: 3899553 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2594. Min Range: -6.2594
Max Act: 5.3844. Min Act: -0.1700
Data Index: 2868179 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19