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

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

Neuron 1668 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.2153. Min Act: -0.0003

Data Index: 778164 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1742. Min Act: -0.0003

Data Index: 520176 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1706. Min Act: -0.0003

Data Index: 115476 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1712. Min Act: -0.0003

Data Index: 1219495 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1708. Min Act: -0.0003

Data Index: 1304973 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1511. Min Act: -0.0003

Data Index: 454134 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1502. Min Act: -0.0002

Data Index: 1042087 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1474. Min Act: -0.0003

Data Index: 1181926 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1484. Min Act: -0.0002

Data Index: 226938 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1406. Min Act: -0.0002

Data Index: 1396563 (Python Code)

Max Activating Token Index: 911

Text #10

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1379. Min Act: -0.0003

Data Index: 934807 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1382. Min Act: -0.0003

Data Index: 109302 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1254. Min Act: -0.0003

Data Index: 136406 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1315. Min Act: -0.0003

Data Index: 441128 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1273. Min Act: -0.0003

Data Index: 1068530 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1234. Min Act: -0.0003

Data Index: 623313 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1303. Min Act: -0.0003

Data Index: 254727 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1261. Min Act: -0.0002

Data Index: 1543828 (Python Code)

Max Activating Token Index: 439

Text #18

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1290. Min Act: -0.0002

Data Index: 1648852 (Python Code)

Max Activating Token Index: 656

Text #19

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1206. Min Act: -0.0003

Data Index: 80335 (C4 (Web Text))

Max Activating Token Index: 125