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

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

Neuron 2943 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.7328. Min Act: -0.0001

Data Index: 710636 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.7153. Min Act: -0.0001

Data Index: 519109 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.6738. Min Act: -0.0000

Data Index: 600472 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.6314. Min Act: -0.0000

Data Index: 633119 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1285921 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5855. Min Act: -0.0001

Data Index: 510907 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.6019. Min Act: -0.0000

Data Index: 1229242 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1182681 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5762. Min Act: -0.0000

Data Index: 863933 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5779. Min Act: -0.0001

Data Index: 1045558 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5565. Min Act: -0.0000

Data Index: 46195 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5536. Min Act: -0.0000

Data Index: 616252 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1334435 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5266. Min Act: -0.0000

Data Index: 1165885 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5562. Min Act: -0.0000

Data Index: 254942 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5214. Min Act: -0.0000

Data Index: 557736 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5349. Min Act: -0.0000

Data Index: 920657 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5326. Min Act: -0.0000

Data Index: 930468 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1319275 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5027. Min Act: -0.0000

Data Index: 392058 (C4 (Web Text))

Max Activating Token Index: 485