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

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

Neuron 3485 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1513163 (Python Code)

Max Activating Token Index: 962

Text #1

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1494413 (Python Code)

Max Activating Token Index: 12

Text #2

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2514. Min Act: -0.0000

Data Index: 1429124 (Python Code)

Max Activating Token Index: 27

Text #3

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2480. Min Act: -0.0000

Data Index: 75742 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2459. Min Act: -0.0000

Data Index: 1554268 (Python Code)

Max Activating Token Index: 146

Text #5

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1443414 (Python Code)

Max Activating Token Index: 637

Text #6

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1460611 (Python Code)

Max Activating Token Index: 67

Text #7

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2111. Min Act: -0.0000

Data Index: 1481469 (Python Code)

Max Activating Token Index: 812

Text #8

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1631570 (Python Code)

Max Activating Token Index: 20

Text #9

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1382760 (Python Code)

Max Activating Token Index: 381

Text #10

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1625195 (Python Code)

Max Activating Token Index: 393

Text #11

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2216. Min Act: -0.0000

Data Index: 1597826 (Python Code)

Max Activating Token Index: 32

Text #12

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1582693 (Python Code)

Max Activating Token Index: 957

Text #13

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1572181 (Python Code)

Max Activating Token Index: 24

Text #14

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2262. Min Act: -0.0000

Data Index: 1530628 (Python Code)

Max Activating Token Index: 11

Text #15

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1646023 (Python Code)

Max Activating Token Index: 85

Text #16

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1497987 (Python Code)

Max Activating Token Index: 668

Text #17

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1418896 (Python Code)

Max Activating Token Index: 49

Text #18

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1430451 (Python Code)

Max Activating Token Index: 831

Text #19

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1531878 (Python Code)

Max Activating Token Index: 201