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

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

Neuron 154 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: 7.0373. Min Range: -7.0373

Max Act: 7.0373. Min Act: -0.0000

Data Index: 591903 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 7.0373. Min Range: -7.0373

Max Act: 6.3446. Min Act: -0.0000

Data Index: 722317 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 7.0373. Min Range: -7.0373

Max Act: 6.3153. Min Act: -0.0000

Data Index: 1282314 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 7.0373. Min Range: -7.0373

Max Act: 6.3952. Min Act: -0.0000

Data Index: 850164 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 7.0373. Min Range: -7.0373

Max Act: 6.3335. Min Act: -0.0000

Data Index: 154283 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 7.0373. Min Range: -7.0373

Max Act: 6.2748. Min Act: -0.0000

Data Index: 1025146 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 7.0373. Min Range: -7.0373

Max Act: 6.2244. Min Act: -0.0000

Data Index: 275611 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 7.0373. Min Range: -7.0373

Max Act: 6.0522. Min Act: -0.0000

Data Index: 1223364 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 7.0373. Min Range: -7.0373

Max Act: 6.5190. Min Act: -0.0000

Data Index: 879496 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 7.0373. Min Range: -7.0373

Max Act: 6.1092. Min Act: -0.0000

Data Index: 768629 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 7.0373. Min Range: -7.0373

Max Act: 6.1531. Min Act: -0.0000

Data Index: 1226345 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 7.0373. Min Range: -7.0373

Max Act: 5.9352. Min Act: -0.0000

Data Index: 407686 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 7.0373. Min Range: -7.0373

Max Act: 6.0779. Min Act: -0.0000

Data Index: 874269 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 7.0373. Min Range: -7.0373

Max Act: 6.0509. Min Act: -0.0000

Data Index: 341991 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 7.0373. Min Range: -7.0373

Max Act: 5.8078. Min Act: -0.0000

Data Index: 684311 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 7.0373. Min Range: -7.0373

Max Act: 5.9829. Min Act: -0.0000

Data Index: 604275 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 7.0373. Min Range: -7.0373

Max Act: 5.8305. Min Act: -0.0000

Data Index: 295385 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 7.0373. Min Range: -7.0373

Max Act: 6.1740. Min Act: -0.0000

Data Index: 67363 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 7.0373. Min Range: -7.0373

Max Act: 6.1042. Min Act: -0.0000

Data Index: 860961 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 7.0373. Min Range: -7.0373

Max Act: 5.5681. Min Act: -0.0000

Data Index: 270327 (C4 (Web Text))

Max Activating Token Index: 785