Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3012 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3451. Min Range: -3.3451
Max Act: 3.3451. Min Act: -0.1700
Data Index: 3169378 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3451. Min Range: -3.3451
Max Act: 3.1566. Min Act: -0.1700
Data Index: 2783556 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3451. Min Range: -3.3451
Max Act: 3.0620. Min Act: -0.1700
Data Index: 6314249 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3451. Min Range: -3.3451
Max Act: 2.9831. Min Act: -0.1700
Data Index: 5763302 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3451. Min Range: -3.3451
Max Act: 2.9831. Min Act: -0.1700
Data Index: 6815546 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3451. Min Range: -3.3451
Max Act: 2.9514. Min Act: -0.1700
Data Index: 4673475 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3451. Min Range: -3.3451
Max Act: 2.9673. Min Act: -0.1700
Data Index: 1039861 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3451. Min Range: -3.3451
Max Act: 2.9198. Min Act: -0.1700
Data Index: 1409053 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3451. Min Range: -3.3451
Max Act: 2.8880. Min Act: -0.1700
Data Index: 5763828 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3451. Min Range: -3.3451
Max Act: 2.8880. Min Act: -0.1700
Data Index: 1891470 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3451. Min Range: -3.3451
Max Act: 2.8880. Min Act: -0.1700
Data Index: 7453643 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3451. Min Range: -3.3451
Max Act: 2.9039. Min Act: -0.1700
Data Index: 8775534 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3451. Min Range: -3.3451
Max Act: 2.8563. Min Act: -0.1700
Data Index: 3632768 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3451. Min Range: -3.3451
Max Act: 2.8563. Min Act: -0.1700
Data Index: 6002067 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3451. Min Range: -3.3451
Max Act: 2.8563. Min Act: -0.1700
Data Index: 5530204 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3451. Min Range: -3.3451
Max Act: 2.8404. Min Act: -0.1700
Data Index: 5763303 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3451. Min Range: -3.3451
Max Act: 2.8086. Min Act: -0.1700
Data Index: 3699790 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3451. Min Range: -3.3451
Max Act: 2.8086. Min Act: -0.1700
Data Index: 333341 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3451. Min Range: -3.3451
Max Act: 2.8086. Min Act: -0.1700
Data Index: 5431916 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3451. Min Range: -3.3451
Max Act: 2.8245. Min Act: -0.1700
Data Index: 3166308 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19