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

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

Neuron 3217 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0222. Min Range: -1.0222

Max Act: 1.0222. Min Act: -0.0001

Data Index: 1250701 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.8733. Min Act: -0.0001

Data Index: 1212921 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.7599. Min Act: -0.0001

Data Index: 551337 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.7912. Min Act: -0.0001

Data Index: 586437 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.7282. Min Act: -0.0001

Data Index: 251747 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6793. Min Act: -0.0001

Data Index: 1287580 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6701. Min Act: -0.0001

Data Index: 1291728 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6511. Min Act: -0.0001

Data Index: 293170 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.7319. Min Act: -0.0001

Data Index: 1169824 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6481. Min Act: -0.0001

Data Index: 491781 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6720. Min Act: -0.0001

Data Index: 329980 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6495. Min Act: -0.0001

Data Index: 925891 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6214. Min Act: -0.0001

Data Index: 839282 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6584. Min Act: -0.0001

Data Index: 355799 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6634. Min Act: -0.0001

Data Index: 394390 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6585. Min Act: -0.0001

Data Index: 79342 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6100. Min Act: -0.0001

Data Index: 1045925 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6051. Min Act: -0.0001

Data Index: 1129002 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6619. Min Act: -0.0001

Data Index: 446638 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6541. Min Act: -0.0001

Data Index: 109535 (C4 (Web Text))

Max Activating Token Index: 160