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

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

Neuron 805 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1671. Min Act: -0.0006

Data Index: 677773 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1482. Min Act: -0.0005

Data Index: 858789 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1277. Min Act: -0.0005

Data Index: 988750 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1099. Min Act: -0.0005

Data Index: 1090399 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1310. Min Act: -0.0005

Data Index: 433290 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1413. Min Act: -0.0005

Data Index: 1313958 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1278. Min Act: -0.0006

Data Index: 118016 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1391. Min Act: -0.0005

Data Index: 33978 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1298. Min Act: -0.0005

Data Index: 1257997 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1291. Min Act: -0.0005

Data Index: 167759 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1338. Min Act: -0.0005

Data Index: 1265437 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1261. Min Act: -0.0005

Data Index: 909599 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1278. Min Act: -0.0005

Data Index: 709496 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1231. Min Act: -0.0006

Data Index: 474771 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1120. Min Act: -0.0005

Data Index: 281446 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1323. Min Act: -0.0006

Data Index: 331658 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1195. Min Act: -0.0005

Data Index: 163251 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1244. Min Act: -0.0005

Data Index: 387590 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1252. Min Act: -0.0005

Data Index: 781963 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1250. Min Act: -0.0005

Data Index: 1092424 (C4 (Web Text))

Max Activating Token Index: 626