Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1034 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0290. Min Act: -0.0005

Data Index: 935787 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0281. Min Act: -0.0005

Data Index: 910343 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0257. Min Act: -0.0005

Data Index: 884874 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0229. Min Act: -0.0005

Data Index: 968732 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0221. Min Act: -0.0005

Data Index: 862621 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0224. Min Act: -0.0005

Data Index: 556923 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0224. Min Act: -0.0005

Data Index: 686514 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0241. Min Act: -0.0005

Data Index: 1320005 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0207. Min Act: -0.0005

Data Index: 582737 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0231. Min Act: -0.0005

Data Index: 1269267 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0240. Min Act: -0.0005

Data Index: 851804 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0217. Min Act: -0.0005

Data Index: 1251313 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0226. Min Act: -0.0005

Data Index: 224514 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0221. Min Act: -0.0005

Data Index: 547399 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0218. Min Act: -0.0005

Data Index: 26530 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0219. Min Act: -0.0005

Data Index: 194847 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0202. Min Act: -0.0005

Data Index: 350305 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0212. Min Act: -0.0005

Data Index: 37272 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0221. Min Act: -0.0005

Data Index: 605053 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0215. Min Act: -0.0005

Data Index: 116200 (C4 (Web Text))

Max Activating Token Index: 756