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

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

Neuron 687 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6652. Min Range: -4.6652

Max Act: 4.6652. Min Act: -0.0000

Data Index: 347043 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 4.6652. Min Range: -4.6652

Max Act: 4.4386. Min Act: -0.0000

Data Index: 1283629 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 4.6652. Min Range: -4.6652

Max Act: 4.2657. Min Act: -0.0000

Data Index: 218610 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 4.6652. Min Range: -4.6652

Max Act: 4.3863. Min Act: -0.0000

Data Index: 835288 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 4.6652. Min Range: -4.6652

Max Act: 4.4199. Min Act: -0.0000

Data Index: 1077897 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 4.6652. Min Range: -4.6652

Max Act: 4.2556. Min Act: -0.0000

Data Index: 327203 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 4.6652. Min Range: -4.6652

Max Act: 4.2190. Min Act: -0.0000

Data Index: 481074 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 4.6652. Min Range: -4.6652

Max Act: 4.3299. Min Act: -0.0000

Data Index: 576504 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 4.6652. Min Range: -4.6652

Max Act: 4.5298. Min Act: -0.0000

Data Index: 1240529 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 4.6652. Min Range: -4.6652

Max Act: 4.1631. Min Act: -0.0000

Data Index: 131229 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 4.6652. Min Range: -4.6652

Max Act: 4.1985. Min Act: -0.0000

Data Index: 939675 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 4.6652. Min Range: -4.6652

Max Act: 4.0990. Min Act: -0.0000

Data Index: 744102 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 4.6652. Min Range: -4.6652

Max Act: 3.9376. Min Act: -0.0000

Data Index: 484275 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 4.6652. Min Range: -4.6652

Max Act: 4.0949. Min Act: -0.0000

Data Index: 1211640 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 4.6652. Min Range: -4.6652

Max Act: 3.8998. Min Act: -0.0000

Data Index: 473463 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 4.6652. Min Range: -4.6652

Max Act: 4.2349. Min Act: -0.0000

Data Index: 44648 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 4.6652. Min Range: -4.6652

Max Act: 4.0586. Min Act: -0.0000

Data Index: 721339 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 4.6652. Min Range: -4.6652

Max Act: 4.0121. Min Act: -0.0000

Data Index: 803863 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 4.6652. Min Range: -4.6652

Max Act: 3.9444. Min Act: -0.0000

Data Index: 496307 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 4.6652. Min Range: -4.6652

Max Act: 4.0929. Min Act: -0.0000

Data Index: 1351048 (C4 (Web Text))

Max Activating Token Index: 358