Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 912 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0387. Min Range: -3.0387
Max Act: 3.0230. Min Act: -0.1700
Data Index: 631430 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0387. Min Range: -3.0387
Max Act: 3.0387. Min Act: -0.1700
Data Index: 696741 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0387. Min Range: -3.0387
Max Act: 3.0072. Min Act: -0.1700
Data Index: 631420 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.9914. Min Act: -0.1700
Data Index: 4517167 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.9755. Min Act: -0.1700
Data Index: 631437 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.8805. Min Act: -0.1700
Data Index: 631423 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.8646. Min Act: -0.1700
Data Index: 7366178 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.8487. Min Act: -0.1700
Data Index: 631435 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.8169. Min Act: -0.1700
Data Index: 631422 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.8010. Min Act: -0.1700
Data Index: 631431 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.8010. Min Act: -0.1700
Data Index: 696744 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.7691. Min Act: -0.1700
Data Index: 696746 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.7691. Min Act: -0.1700
Data Index: 696757 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.7532. Min Act: -0.1700
Data Index: 612505 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.7372. Min Act: -0.1700
Data Index: 4517172 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.7212. Min Act: -0.1700
Data Index: 631428 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.7212. Min Act: -0.1700
Data Index: 4517171 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.6892. Min Act: -0.1700
Data Index: 140473 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.7052. Min Act: -0.1700
Data Index: 1784602 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.7212. Min Act: -0.1700
Data Index: 696749 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19