Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 245 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2934. Min Act: -0.0000

Data Index: 570175 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2635. Min Act: -0.0000

Data Index: 807878 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2532. Min Act: -0.0000

Data Index: 649189 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2355. Min Act: -0.0000

Data Index: 880502 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2242. Min Act: -0.0000

Data Index: 168468 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2350. Min Act: -0.0000

Data Index: 904860 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2313. Min Act: -0.0000

Data Index: 265713 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2353. Min Act: -0.0000

Data Index: 846541 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1383799 (Python Code)

Max Activating Token Index: 17

Text #9

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2132. Min Act: -0.0000

Data Index: 885419 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1304268 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1042474 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2078. Min Act: -0.0000

Data Index: 1223741 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1316652 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1984. Min Act: -0.0000

Data Index: 267988 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1979. Min Act: -0.0000

Data Index: 413827 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1018082 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1960. Min Act: -0.0000

Data Index: 926993 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2023. Min Act: -0.0000

Data Index: 671939 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1950. Min Act: -0.0000

Data Index: 903381 (C4 (Web Text))

Max Activating Token Index: 808