Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1676 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1553. Min Act: -0.0003

Data Index: 1236758 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1536. Min Act: -0.0003

Data Index: 238743 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1458. Min Act: -0.0004

Data Index: 795132 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1425. Min Act: -0.0003

Data Index: 89399 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1411. Min Act: -0.0003

Data Index: 1319192 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1403. Min Act: -0.0003

Data Index: 870738 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1396. Min Act: -0.0003

Data Index: 753407 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1325. Min Act: -0.0003

Data Index: 298562 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1335. Min Act: -0.0003

Data Index: 1029574 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1307. Min Act: -0.0003

Data Index: 382650 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1285. Min Act: -0.0004

Data Index: 1079791 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1241. Min Act: -0.0003

Data Index: 726534 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1246. Min Act: -0.0003

Data Index: 329900 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1201. Min Act: -0.0003

Data Index: 1344531 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1217. Min Act: -0.0003

Data Index: 573550 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1226. Min Act: -0.0003

Data Index: 677443 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1223. Min Act: -0.0003

Data Index: 100854 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1181. Min Act: -0.0003

Data Index: 139768 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1200. Min Act: -0.0003

Data Index: 1295529 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1170. Min Act: -0.0003

Data Index: 459096 (C4 (Web Text))

Max Activating Token Index: 239