Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2559 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2315. Min Range: -1.2315

Max Act: 1.2315. Min Act: -0.0000

Data Index: 1247067 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 1.2315. Min Range: -1.2315

Max Act: 1.0467. Min Act: -0.0000

Data Index: 578995 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 1.2315. Min Range: -1.2315

Max Act: 1.1200. Min Act: -0.0000

Data Index: 581562 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 1.2315. Min Range: -1.2315

Max Act: 1.1470. Min Act: -0.0000

Data Index: 654976 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 1.2315. Min Range: -1.2315

Max Act: 1.0392. Min Act: -0.0000

Data Index: 1112965 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.9840. Min Act: -0.0000

Data Index: 522894 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.9920. Min Act: -0.0000

Data Index: 88865 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 1.2315. Min Range: -1.2315

Max Act: 1.0130. Min Act: -0.0000

Data Index: 428877 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 1.2315. Min Range: -1.2315

Max Act: 1.0038. Min Act: -0.0000

Data Index: 1016819 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.9968. Min Act: -0.0000

Data Index: 107661 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.9347. Min Act: -0.0000

Data Index: 304354 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.9212. Min Act: -0.0001

Data Index: 297070 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8917. Min Act: -0.0001

Data Index: 929874 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.9073. Min Act: -0.0000

Data Index: 193790 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.9564. Min Act: -0.0000

Data Index: 133178 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.9409. Min Act: -0.0000

Data Index: 754440 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8645. Min Act: -0.0000

Data Index: 69177 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.9323. Min Act: 0.0000

Data Index: 40220 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.9017. Min Act: -0.0000

Data Index: 531928 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.9030. Min Act: -0.0000

Data Index: 1026095 (C4 (Web Text))

Max Activating Token Index: 962