Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 191 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1453. Min Act: -0.0002

Data Index: 171745 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1361. Min Act: -0.0002

Data Index: 1118674 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1338. Min Act: -0.0002

Data Index: 1142186 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1339. Min Act: -0.0002

Data Index: 924041 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1314. Min Act: -0.0002

Data Index: 308599 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1308. Min Act: -0.0002

Data Index: 836244 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1322. Min Act: -0.0002

Data Index: 190538 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1332. Min Act: -0.0002

Data Index: 1189415 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1330. Min Act: -0.0002

Data Index: 104916 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1319. Min Act: -0.0002

Data Index: 749471 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1315. Min Act: -0.0002

Data Index: 1230063 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1311. Min Act: -0.0002

Data Index: 22463 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1257. Min Act: -0.0002

Data Index: 1252348 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1308. Min Act: -0.0002

Data Index: 1246191 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1293. Min Act: -0.0002

Data Index: 449164 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1304. Min Act: -0.0002

Data Index: 748525 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1297. Min Act: -0.0002

Data Index: 520203 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1289. Min Act: -0.0002

Data Index: 1255454 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1281. Min Act: -0.0002

Data Index: 608066 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1316. Min Act: -0.0002

Data Index: 1262536 (C4 (Web Text))

Max Activating Token Index: 222