Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2096 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.9530. Min Act: -0.1700
Data Index: 8234096 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.9530. Min Act: -0.1700
Data Index: 663263 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.9218. Min Act: -0.1700
Data Index: 5220335 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.9530. Min Act: -0.1700
Data Index: 6944647 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.7968. Min Act: -0.1700
Data Index: 5054366 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.8280. Min Act: -0.1700
Data Index: 3420034 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.8280. Min Act: -0.1700
Data Index: 2058431 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.7030. Min Act: -0.1700
Data Index: 154690 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.7030. Min Act: -0.1700
Data Index: 3167920 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.7030. Min Act: -0.1700
Data Index: 5054373 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.7030. Min Act: -0.1700
Data Index: 8683392 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.7343. Min Act: -0.1700
Data Index: 5054365 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.7343. Min Act: -0.1700
Data Index: 5220336 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.6718. Min Act: -0.1700
Data Index: 1385393 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.6718. Min Act: -0.1700
Data Index: 8078731 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.6718. Min Act: -0.1700
Data Index: 663265 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.6093. Min Act: -0.1700
Data Index: 6629191 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.6405. Min Act: -0.1700
Data Index: 663264 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.6718. Min Act: -0.1700
Data Index: 8564980 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9530. Min Range: -7.9530
Max Act: 7.5780. Min Act: -0.1700
Data Index: 7468268 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19