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

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

Neuron 4806 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: 0.5517. Min Range: -0.5517

Max Act: 0.5517. Min Act: -0.0000

Data Index: 146819 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.5256. Min Act: -0.0000

Data Index: 680787 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.5044. Min Act: -0.0000

Data Index: 120324 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.5050. Min Act: -0.0000

Data Index: 418314 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.4886. Min Act: -0.0000

Data Index: 1059474 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.4934. Min Act: -0.0000

Data Index: 74243 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.4344. Min Act: -0.0000

Data Index: 563311 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.4246. Min Act: -0.0000

Data Index: 214583 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1215048 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1095135 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3770. Min Act: -0.0000

Data Index: 144747 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3817. Min Act: -0.0000

Data Index: 773239 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.4144. Min Act: -0.0000

Data Index: 733547 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1295032 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3939. Min Act: -0.0000

Data Index: 764111 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3773. Min Act: -0.0000

Data Index: 112387 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3526. Min Act: -0.0000

Data Index: 1056351 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3503. Min Act: -0.0000

Data Index: 1039455 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3446. Min Act: -0.0000

Data Index: 1389093 (Python Code)

Max Activating Token Index: 508

Text #19

Max Range: 0.5517. Min Range: -0.5517

Max Act: 0.3895. Min Act: -0.0000

Data Index: 24878 (C4 (Web Text))

Max Activating Token Index: 58