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

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

Neuron 4093 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: 0.1784. Min Range: -0.1784

Max Act: 0.1784. Min Act: -0.0001

Data Index: 804393 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1667. Min Act: -0.0001

Data Index: 516448 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1511. Min Act: -0.0001

Data Index: 331377 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1445. Min Act: -0.0001

Data Index: 1110595 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1244. Min Act: -0.0001

Data Index: 689989 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1392. Min Act: -0.0001

Data Index: 391350 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1233614 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1293. Min Act: -0.0001

Data Index: 157997 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1332. Min Act: -0.0001

Data Index: 71400 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1160684 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1190229 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1391. Min Act: -0.0001

Data Index: 1199449 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1050061 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1233. Min Act: -0.0001

Data Index: 901150 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1318. Min Act: -0.0001

Data Index: 983499 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1260. Min Act: -0.0001

Data Index: 279080 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1353. Min Act: -0.0001

Data Index: 1328926 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1332. Min Act: -0.0001

Data Index: 696983 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1148. Min Act: -0.0001

Data Index: 499228 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1223. Min Act: -0.0001

Data Index: 107706 (C4 (Web Text))

Max Activating Token Index: 1014