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

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

Neuron 267 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1432. Min Act: -0.0002

Data Index: 861532 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1478. Min Act: -0.0001

Data Index: 1209810 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1449. Min Act: -0.0001

Data Index: 1437075 (Python Code)

Max Activating Token Index: 702

Text #3

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1367. Min Act: -0.0002

Data Index: 439835 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1368. Min Act: -0.0001

Data Index: 55260 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1240. Min Act: -0.0001

Data Index: 82841 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1292. Min Act: -0.0002

Data Index: 1112889 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1308208 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1316. Min Act: -0.0002

Data Index: 839543 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1380. Min Act: -0.0001

Data Index: 454612 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1338. Min Act: -0.0002

Data Index: 1206720 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1260. Min Act: -0.0002

Data Index: 993541 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1208. Min Act: -0.0001

Data Index: 1267280 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1282. Min Act: -0.0002

Data Index: 170041 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1314. Min Act: -0.0002

Data Index: 1320926 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1311. Min Act: -0.0002

Data Index: 899776 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1310. Min Act: -0.0002

Data Index: 957204 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1211. Min Act: -0.0002

Data Index: 103830 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1263. Min Act: -0.0002

Data Index: 1011988 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1210. Min Act: -0.0001

Data Index: 40632 (C4 (Web Text))

Max Activating Token Index: 974