Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3375 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1663. Min Act: -0.0002

Data Index: 131365 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1689. Min Act: -0.0002

Data Index: 1102036 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.2438. Min Act: -0.0002

Data Index: 3110 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1283. Min Act: -0.0002

Data Index: 357673 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1440. Min Act: -0.0002

Data Index: 289430 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1412. Min Act: -0.0002

Data Index: 325181 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1426. Min Act: -0.0002

Data Index: 147819 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1396. Min Act: -0.0002

Data Index: 1060776 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1294. Min Act: -0.0002

Data Index: 513255 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1403. Min Act: -0.0002

Data Index: 532421 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1293. Min Act: -0.0002

Data Index: 949084 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1301. Min Act: -0.0002

Data Index: 1274274 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1366. Min Act: -0.0002

Data Index: 1052195 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1320. Min Act: -0.0002

Data Index: 1207574 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1448. Min Act: -0.0002

Data Index: 136751 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1391. Min Act: -0.0002

Data Index: 1043803 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1248. Min Act: -0.0002

Data Index: 1310612 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1250. Min Act: -0.0002

Data Index: 226589 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1385. Min Act: -0.0002

Data Index: 261090 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.2438. Min Range: -0.2438

Max Act: 0.1433. Min Act: -0.0002

Data Index: 18392 (C4 (Web Text))

Max Activating Token Index: 910