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

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

Neuron 901 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0541. Min Range: -6.0541

Max Act: 6.0541. Min Act: -0.0000

Data Index: 1352464 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 6.0541. Min Range: -6.0541

Max Act: 5.6537. Min Act: -0.0000

Data Index: 541699 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 6.0541. Min Range: -6.0541

Max Act: 5.5775. Min Act: -0.0000

Data Index: 36885 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 6.0541. Min Range: -6.0541

Max Act: 5.5473. Min Act: -0.0000

Data Index: 1327296 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 6.0541. Min Range: -6.0541

Max Act: 5.2975. Min Act: -0.0000

Data Index: 358653 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 6.0541. Min Range: -6.0541

Max Act: 5.0150. Min Act: -0.0000

Data Index: 1283077 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 6.0541. Min Range: -6.0541

Max Act: 5.1874. Min Act: -0.0000

Data Index: 1294174 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 6.0541. Min Range: -6.0541

Max Act: 4.7678. Min Act: -0.0000

Data Index: 1006725 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 6.0541. Min Range: -6.0541

Max Act: 5.1035. Min Act: -0.0000

Data Index: 848301 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 6.0541. Min Range: -6.0541

Max Act: 5.0241. Min Act: -0.0000

Data Index: 666677 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 6.0541. Min Range: -6.0541

Max Act: 4.8266. Min Act: -0.0000

Data Index: 330239 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 6.0541. Min Range: -6.0541

Max Act: 4.9350. Min Act: -0.0000

Data Index: 942279 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 6.0541. Min Range: -6.0541

Max Act: 4.7086. Min Act: -0.0000

Data Index: 1151015 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 6.0541. Min Range: -6.0541

Max Act: 4.6488. Min Act: -0.0000

Data Index: 17101 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 6.0541. Min Range: -6.0541

Max Act: 4.7211. Min Act: -0.0000

Data Index: 114063 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 6.0541. Min Range: -6.0541

Max Act: 4.6768. Min Act: -0.0000

Data Index: 584169 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 6.0541. Min Range: -6.0541

Max Act: 4.3168. Min Act: -0.0000

Data Index: 1087711 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 6.0541. Min Range: -6.0541

Max Act: 4.5744. Min Act: -0.0000

Data Index: 790961 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 6.0541. Min Range: -6.0541

Max Act: 4.0196. Min Act: -0.0000

Data Index: 265956 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 6.0541. Min Range: -6.0541

Max Act: 4.1667. Min Act: -0.0000

Data Index: 849669 (C4 (Web Text))

Max Activating Token Index: 722