Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3255 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.5974. Min Act: -0.1700
Data Index: 6920341 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.5974. Min Act: -0.1700
Data Index: 4291045 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.5349. Min Act: -0.1700
Data Index: 2594870 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.5037. Min Act: -0.1700
Data Index: 3643395 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.4724. Min Act: -0.1700
Data Index: 5439762 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.4412. Min Act: -0.1700
Data Index: 6676748 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.4099. Min Act: -0.1700
Data Index: 2194309 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.4412. Min Act: -0.1700
Data Index: 1640966 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.4099. Min Act: -0.1700
Data Index: 4866871 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.3787. Min Act: -0.1700
Data Index: 2875335 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.3787. Min Act: -0.1700
Data Index: 8278630 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.3474. Min Act: -0.1700
Data Index: 7932333 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.3162. Min Act: -0.1700
Data Index: 7708372 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.3162. Min Act: -0.1700
Data Index: 6100704 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.2849. Min Act: -0.1700
Data Index: 2444161 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.3162. Min Act: -0.1700
Data Index: 1200428 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.3162. Min Act: -0.1700
Data Index: 7436064 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.3162. Min Act: -0.1700
Data Index: 1395428 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.3474. Min Act: -0.1700
Data Index: 230658 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5974. Min Range: -4.5974
Max Act: 4.3162. Min Act: -0.1700
Data Index: 6016369 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19