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

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

Neuron 350 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: 1.3532. Min Range: -1.3532

Max Act: 1.2349. Min Act: -0.0001

Data Index: 460336 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.3532. Min Act: -0.0000

Data Index: 852646 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.2780. Min Act: -0.0000

Data Index: 572944 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.2399. Min Act: -0.0000

Data Index: 412138 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.2122. Min Act: -0.0000

Data Index: 915283 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.0765. Min Act: -0.0000

Data Index: 301759 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.1619. Min Act: -0.0001

Data Index: 13487 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.1337. Min Act: -0.0000

Data Index: 412928 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.0597. Min Act: -0.0000

Data Index: 624064 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.0031. Min Act: -0.0000

Data Index: 152226 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.0304. Min Act: -0.0000

Data Index: 915190 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.0349. Min Act: -0.0001

Data Index: 709743 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.0205. Min Act: -0.0000

Data Index: 909148 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 1.3532. Min Range: -1.3532

Max Act: 0.9634. Min Act: -0.0000

Data Index: 1033877 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 1.3532. Min Range: -1.3532

Max Act: 0.8974. Min Act: -0.0001

Data Index: 354286 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.0384. Min Act: -0.0001

Data Index: 109810 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 1.3532. Min Range: -1.3532

Max Act: 0.9987. Min Act: -0.0000

Data Index: 708151 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 1.3532. Min Range: -1.3532

Max Act: 0.9539. Min Act: -0.0000

Data Index: 434677 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 1.3532. Min Range: -1.3532

Max Act: 0.9270. Min Act: -0.0000

Data Index: 544352 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 1.3532. Min Range: -1.3532

Max Act: 0.9361. Min Act: -0.0000

Data Index: 658165 (C4 (Web Text))

Max Activating Token Index: 416