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

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

Neuron 305 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1228404 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1587. Min Act: -0.0000

Data Index: 746134 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1462. Min Act: -0.0000

Data Index: 503584 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1401. Min Act: -0.0001

Data Index: 646742 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1460. Min Act: -0.0001

Data Index: 835328 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1551. Min Act: -0.0000

Data Index: 25467 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1454. Min Act: -0.0000

Data Index: 894056 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1382. Min Act: -0.0001

Data Index: 1605624 (Python Code)

Max Activating Token Index: 669

Text #8

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1355. Min Act: -0.0000

Data Index: 1298875 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1250. Min Act: -0.0000

Data Index: 702668 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1292. Min Act: -0.0000

Data Index: 826360 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1340. Min Act: -0.0000

Data Index: 345856 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1148067 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1247. Min Act: -0.0000

Data Index: 508344 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1411594 (Python Code)

Max Activating Token Index: 52

Text #15

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1282. Min Act: -0.0000

Data Index: 7163 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1270. Min Act: -0.0001

Data Index: 272543 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1259. Min Act: -0.0000

Data Index: 61243 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1223. Min Act: -0.0000

Data Index: 999686 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.1691. Min Range: -0.1691

Max Act: 0.1222. Min Act: -0.0000

Data Index: 664750 (C4 (Web Text))

Max Activating Token Index: 263