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

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

Neuron 4743 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.7228. Min Act: -0.0000

Data Index: 923685 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.5609. Min Act: -0.0001

Data Index: 573296 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.7128. Min Act: -0.0000

Data Index: 1252576 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.4118. Min Act: -0.0000

Data Index: 958016 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.3142. Min Act: -0.0000

Data Index: 655888 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.4768. Min Act: -0.0000

Data Index: 90326 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.2947. Min Act: -0.0000

Data Index: 700695 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.2260. Min Act: -0.0000

Data Index: 1343563 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.4449. Min Act: -0.0000

Data Index: 217786 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.2243. Min Act: -0.0000

Data Index: 1339673 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.2847. Min Act: -0.0000

Data Index: 267747 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.2817. Min Act: -0.0000

Data Index: 491231 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.3464. Min Act: -0.0000

Data Index: 991860 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.2366. Min Act: -0.0000

Data Index: 865663 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.2046. Min Act: -0.0000

Data Index: 223706 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.2594. Min Act: -0.0000

Data Index: 413228 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.2559. Min Act: -0.0000

Data Index: 197903 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1062452 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.1361. Min Act: -0.0000

Data Index: 601244 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 1.7228. Min Range: -1.7228

Max Act: 1.3663. Min Act: -0.0000

Data Index: 787261 (C4 (Web Text))

Max Activating Token Index: 933