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

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

Neuron 230 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1667. Min Act: -0.0001

Data Index: 1530823 (Python Code)

Max Activating Token Index: 50

Text #1

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1529. Min Act: -0.0001

Data Index: 1014674 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1266. Min Act: -0.0001

Data Index: 395393 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1301. Min Act: -0.0001

Data Index: 177607 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1286. Min Act: -0.0001

Data Index: 1391594 (Python Code)

Max Activating Token Index: 650

Text #5

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1340. Min Act: -0.0001

Data Index: 585481 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1347. Min Act: -0.0001

Data Index: 1370878 (Python Code)

Max Activating Token Index: 195

Text #7

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1376932 (Python Code)

Max Activating Token Index: 143

Text #8

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1234. Min Act: -0.0001

Data Index: 683180 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1275. Min Act: -0.0001

Data Index: 535957 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1172. Min Act: -0.0001

Data Index: 516119 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1217. Min Act: -0.0001

Data Index: 899676 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1204. Min Act: -0.0001

Data Index: 1613389 (Python Code)

Max Activating Token Index: 267

Text #13

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1226. Min Act: -0.0001

Data Index: 1510667 (Python Code)

Max Activating Token Index: 553

Text #14

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1188. Min Act: -0.0001

Data Index: 457296 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1194. Min Act: -0.0001

Data Index: 1270979 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1298. Min Act: -0.0001

Data Index: 1508620 (Python Code)

Max Activating Token Index: 310

Text #17

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1151. Min Act: -0.0001

Data Index: 41588 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1109. Min Act: -0.0001

Data Index: 147731 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1148. Min Act: -0.0001

Data Index: 1512339 (Python Code)

Max Activating Token Index: 472