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

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

Neuron 4808 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0304. Min Act: -0.0003

Data Index: 734734 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0290. Min Act: -0.0003

Data Index: 361001 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0277. Min Act: -0.0002

Data Index: 526763 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0263. Min Act: -0.0003

Data Index: 786123 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0262. Min Act: -0.0003

Data Index: 746520 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0279. Min Act: -0.0003

Data Index: 349134 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0243. Min Act: -0.0003

Data Index: 294674 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1325470 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0243. Min Act: -0.0002

Data Index: 57787 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0235. Min Act: -0.0003

Data Index: 64001 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0238. Min Act: -0.0003

Data Index: 273323 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0229. Min Act: -0.0003

Data Index: 682757 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0240. Min Act: -0.0003

Data Index: 466514 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1170753 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0230. Min Act: -0.0003

Data Index: 508989 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0220. Min Act: -0.0003

Data Index: 485178 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1079009 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0217. Min Act: -0.0002

Data Index: 47530 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0221. Min Act: -0.0003

Data Index: 100194 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0229. Min Act: -0.0003

Data Index: 4500 (C4 (Web Text))

Max Activating Token Index: 692