Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 291 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.6063. Min Act: -0.1700
Data Index: 1032860 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.4813. Min Act: -0.1700
Data Index: 8535661 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.4500. Min Act: -0.1700
Data Index: 6117830 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.3875. Min Act: -0.1700
Data Index: 8384957 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.4500. Min Act: -0.1700
Data Index: 5331858 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.2938. Min Act: -0.1700
Data Index: 1389482 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.3563. Min Act: -0.1700
Data Index: 2307534 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.3563. Min Act: -0.1700
Data Index: 8676942 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.3250. Min Act: -0.1700
Data Index: 8141769 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.3250. Min Act: -0.1700
Data Index: 5342484 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.2938. Min Act: -0.1700
Data Index: 7277905 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.1688. Min Act: -0.1700
Data Index: 4853052 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.2938. Min Act: -0.1700
Data Index: 561871 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.2625. Min Act: -0.1700
Data Index: 4727249 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.1375. Min Act: -0.1700
Data Index: 1111114 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.2625. Min Act: -0.1700
Data Index: 5853375 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.2000. Min Act: -0.1700
Data Index: 2876955 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.2313. Min Act: -0.1700
Data Index: 2993600 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.2938. Min Act: -0.1700
Data Index: 288940 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6063. Min Range: -5.6063
Max Act: 5.2625. Min Act: -0.1700
Data Index: 8548678 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19