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

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

Neuron 4302 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: 0.1518. Min Range: -0.1518

Max Act: 0.1491. Min Act: -0.0003

Data Index: 1598865 (Python Code)

Max Activating Token Index: 182

Text #1

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1518. Min Act: -0.0002

Data Index: 1634259 (Python Code)

Max Activating Token Index: 376

Text #2

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1376. Min Act: -0.0003

Data Index: 1521598 (Python Code)

Max Activating Token Index: 459

Text #3

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1314. Min Act: -0.0003

Data Index: 1480384 (Python Code)

Max Activating Token Index: 224

Text #4

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1407. Min Act: -0.0003

Data Index: 1373379 (Python Code)

Max Activating Token Index: 228

Text #5

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1356. Min Act: -0.0002

Data Index: 1475995 (Python Code)

Max Activating Token Index: 737

Text #6

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1403. Min Act: -0.0002

Data Index: 1441174 (Python Code)

Max Activating Token Index: 43

Text #7

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1179. Min Act: -0.0003

Data Index: 1599311 (Python Code)

Max Activating Token Index: 416

Text #8

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1154. Min Act: -0.0003

Data Index: 1523469 (Python Code)

Max Activating Token Index: 447

Text #9

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1156. Min Act: -0.0002

Data Index: 816741 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1096. Min Act: -0.0002

Data Index: 1556733 (Python Code)

Max Activating Token Index: 389

Text #11

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1026. Min Act: -0.0003

Data Index: 1610559 (Python Code)

Max Activating Token Index: 260

Text #12

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1094. Min Act: -0.0002

Data Index: 99281 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1072. Min Act: -0.0002

Data Index: 1417212 (Python Code)

Max Activating Token Index: 122

Text #14

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1031. Min Act: -0.0003

Data Index: 695185 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1068. Min Act: -0.0003

Data Index: 1362535 (Python Code)

Max Activating Token Index: 301

Text #16

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1063. Min Act: -0.0002

Data Index: 1501215 (Python Code)

Max Activating Token Index: 425

Text #17

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.0989. Min Act: -0.0002

Data Index: 901793 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.0946. Min Act: -0.0003

Data Index: 3506 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.0933. Min Act: -0.0003

Data Index: 1588405 (Python Code)

Max Activating Token Index: 780