Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1504 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1408. Min Act: -0.0003

Data Index: 210680 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1405. Min Act: -0.0004

Data Index: 456338 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1395. Min Act: -0.0003

Data Index: 621595 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1330. Min Act: -0.0003

Data Index: 1182823 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1429. Min Act: -0.0003

Data Index: 647645 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1353. Min Act: -0.0003

Data Index: 788821 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1373. Min Act: -0.0003

Data Index: 351675 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1262. Min Act: -0.0003

Data Index: 1057124 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1241. Min Act: -0.0003

Data Index: 692088 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1332. Min Act: -0.0003

Data Index: 1092154 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1289. Min Act: -0.0003

Data Index: 634072 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1282. Min Act: -0.0003

Data Index: 729570 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1320. Min Act: -0.0003

Data Index: 499440 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1258. Min Act: -0.0003

Data Index: 576733 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1265. Min Act: -0.0003

Data Index: 384352 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1286. Min Act: -0.0003

Data Index: 341355 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1260. Min Act: -0.0003

Data Index: 1116453 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1251. Min Act: -0.0003

Data Index: 475586 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1211. Min Act: -0.0004

Data Index: 644889 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1206. Min Act: -0.0003

Data Index: 1244879 (C4 (Web Text))

Max Activating Token Index: 545