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

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

Neuron 3520 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.9545. Min Act: -0.0000

Data Index: 236028 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.7973. Min Act: -0.0000

Data Index: 298776 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.7279. Min Act: -0.0000

Data Index: 55546 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6417. Min Act: -0.0000

Data Index: 651857 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.5559. Min Act: -0.0000

Data Index: 1310675 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.5547. Min Act: -0.0000

Data Index: 1256743 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1353050 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.5308. Min Act: -0.0000

Data Index: 167825 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1110145 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.4300. Min Act: -0.0000

Data Index: 264465 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1240618 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.4119. Min Act: -0.0000

Data Index: 379976 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.4915. Min Act: -0.0000

Data Index: 1093134 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.5027. Min Act: -0.0000

Data Index: 784082 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1025238 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.4453. Min Act: -0.0000

Data Index: 282279 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.4768. Min Act: -0.0000

Data Index: 426819 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.4039. Min Act: -0.0000

Data Index: 889557 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.4162. Min Act: -0.0000

Data Index: 796452 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.4351. Min Act: -0.0000

Data Index: 470613 (C4 (Web Text))

Max Activating Token Index: 564