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

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

Neuron 5646 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1350. Min Range: -1.1350

Max Act: 1.0716. Min Act: -0.0000

Data Index: 1614342 (Python Code)

Max Activating Token Index: 326

Text #1

Max Range: 1.1350. Min Range: -1.1350

Max Act: 1.1350. Min Act: -0.0000

Data Index: 641889 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 1.1350. Min Range: -1.1350

Max Act: 1.1044. Min Act: -0.0000

Data Index: 1436436 (Python Code)

Max Activating Token Index: 136

Text #3

Max Range: 1.1350. Min Range: -1.1350

Max Act: 1.0842. Min Act: -0.0000

Data Index: 1515551 (Python Code)

Max Activating Token Index: 294

Text #4

Max Range: 1.1350. Min Range: -1.1350

Max Act: 1.0165. Min Act: -0.0000

Data Index: 1606610 (Python Code)

Max Activating Token Index: 336

Text #5

Max Range: 1.1350. Min Range: -1.1350

Max Act: 1.0100. Min Act: -0.0000

Data Index: 1550566 (Python Code)

Max Activating Token Index: 359

Text #6

Max Range: 1.1350. Min Range: -1.1350

Max Act: 1.0386. Min Act: -0.0000

Data Index: 1397924 (Python Code)

Max Activating Token Index: 348

Text #7

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9859. Min Act: -0.0000

Data Index: 1364928 (Python Code)

Max Activating Token Index: 735

Text #8

Max Range: 1.1350. Min Range: -1.1350

Max Act: 1.0417. Min Act: -0.0000

Data Index: 1623530 (Python Code)

Max Activating Token Index: 939

Text #9

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9687. Min Act: -0.0000

Data Index: 1535185 (Python Code)

Max Activating Token Index: 848

Text #10

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9513. Min Act: -0.0000

Data Index: 1475704 (Python Code)

Max Activating Token Index: 112

Text #11

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9032. Min Act: -0.0000

Data Index: 1619752 (Python Code)

Max Activating Token Index: 793

Text #12

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9308. Min Act: -0.0000

Data Index: 1543125 (Python Code)

Max Activating Token Index: 112

Text #13

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9316. Min Act: -0.0000

Data Index: 1558148 (Python Code)

Max Activating Token Index: 108

Text #14

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1541309 (Python Code)

Max Activating Token Index: 51

Text #15

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1467538 (Python Code)

Max Activating Token Index: 141

Text #16

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1513812 (Python Code)

Max Activating Token Index: 35

Text #17

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9157. Min Act: -0.0000

Data Index: 1452749 (Python Code)

Max Activating Token Index: 332

Text #18

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9507. Min Act: -0.0000

Data Index: 1503802 (Python Code)

Max Activating Token Index: 322

Text #19

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.8572. Min Act: -0.0000

Data Index: 1368021 (Python Code)

Max Activating Token Index: 535