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

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

Neuron 94 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.6502. Min Act: -0.0001

Data Index: 586180 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5880. Min Act: -0.0000

Data Index: 759780 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1303034 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5616. Min Act: -0.0000

Data Index: 1357105 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5563. Min Act: -0.0000

Data Index: 111942 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5364. Min Act: -0.0000

Data Index: 912381 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.4981. Min Act: -0.0000

Data Index: 519502 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5000. Min Act: -0.0000

Data Index: 1213669 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.4818. Min Act: -0.0000

Data Index: 1307167 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.4952. Min Act: -0.0001

Data Index: 1140860 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.4599. Min Act: -0.0000

Data Index: 216275 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.4526. Min Act: -0.0000

Data Index: 324309 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.4554. Min Act: -0.0000

Data Index: 889010 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.4679. Min Act: -0.0000

Data Index: 998836 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1094868 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.4483. Min Act: -0.0001

Data Index: 294254 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.4393. Min Act: -0.0001

Data Index: 113031 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.4340. Min Act: -0.0000

Data Index: 628125 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.4199. Min Act: -0.0000

Data Index: 410421 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1075758 (C4 (Web Text))

Max Activating Token Index: 956