Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1585 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6304. Min Range: -1.6304

Max Act: 1.6304. Min Act: -0.0000

Data Index: 624379 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 1.6304. Min Range: -1.6304

Max Act: 1.3926. Min Act: -0.0000

Data Index: 270790 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 1.6304. Min Range: -1.6304

Max Act: 1.0429. Min Act: -0.0000

Data Index: 69655 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 1.6304. Min Range: -1.6304

Max Act: 1.1030. Min Act: -0.0000

Data Index: 1172795 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 1.6304. Min Range: -1.6304

Max Act: 0.9941. Min Act: -0.0000

Data Index: 679595 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 1.6304. Min Range: -1.6304

Max Act: 1.0202. Min Act: -0.0000

Data Index: 793328 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 1.6304. Min Range: -1.6304

Max Act: 0.9791. Min Act: -0.0000

Data Index: 692388 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 1.6304. Min Range: -1.6304

Max Act: 0.9252. Min Act: -0.0000

Data Index: 1177997 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 1.6304. Min Range: -1.6304

Max Act: 0.9254. Min Act: -0.0000

Data Index: 956992 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 1.6304. Min Range: -1.6304

Max Act: 0.9479. Min Act: -0.0000

Data Index: 314840 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 1.6304. Min Range: -1.6304

Max Act: 0.9492. Min Act: -0.0000

Data Index: 159625 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 1.6304. Min Range: -1.6304

Max Act: 0.9281. Min Act: -0.0000

Data Index: 193311 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 1.6304. Min Range: -1.6304

Max Act: 0.8762. Min Act: -0.0000

Data Index: 1004587 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 1.6304. Min Range: -1.6304

Max Act: 0.9006. Min Act: -0.0000

Data Index: 490542 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 1.6304. Min Range: -1.6304

Max Act: 0.8597. Min Act: -0.0000

Data Index: 691247 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 1.6304. Min Range: -1.6304

Max Act: 0.8978. Min Act: -0.0000

Data Index: 224571 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 1.6304. Min Range: -1.6304

Max Act: 0.8824. Min Act: -0.0000

Data Index: 14982 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 1.6304. Min Range: -1.6304

Max Act: 0.8392. Min Act: -0.0000

Data Index: 203601 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 1.6304. Min Range: -1.6304

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1286163 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 1.6304. Min Range: -1.6304

Max Act: 0.8318. Min Act: -0.0000

Data Index: 433852 (C4 (Web Text))

Max Activating Token Index: 924