Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1421 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2623. Min Act: -0.0001

Data Index: 1578602 (Python Code)

Max Activating Token Index: 87

Text #1

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2707. Min Act: -0.0001

Data Index: 1531965 (Python Code)

Max Activating Token Index: 99

Text #2

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2650. Min Act: -0.0001

Data Index: 1449778 (Python Code)

Max Activating Token Index: 51

Text #3

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2708. Min Act: -0.0001

Data Index: 1361599 (Python Code)

Max Activating Token Index: 95

Text #4

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2427. Min Act: -0.0001

Data Index: 1640808 (Python Code)

Max Activating Token Index: 30

Text #5

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2500. Min Act: -0.0001

Data Index: 1478104 (Python Code)

Max Activating Token Index: 87

Text #6

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2617. Min Act: -0.0001

Data Index: 1421797 (Python Code)

Max Activating Token Index: 81

Text #7

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2577. Min Act: -0.0001

Data Index: 1397755 (Python Code)

Max Activating Token Index: 23

Text #8

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2658. Min Act: -0.0001

Data Index: 1436416 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2550. Min Act: -0.0001

Data Index: 1450393 (Python Code)

Max Activating Token Index: 72

Text #10

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2522. Min Act: -0.0001

Data Index: 1425260 (Python Code)

Max Activating Token Index: 45

Text #11

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2511. Min Act: -0.0001

Data Index: 1365555 (Python Code)

Max Activating Token Index: 143

Text #12

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2464. Min Act: -0.0001

Data Index: 1471537 (Python Code)

Max Activating Token Index: 206

Text #13

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2314. Min Act: -0.0001

Data Index: 593960 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2208. Min Act: -0.0001

Data Index: 98423 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2371. Min Act: -0.0001

Data Index: 1627732 (Python Code)

Max Activating Token Index: 187

Text #16

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2435. Min Act: -0.0001

Data Index: 1404969 (Python Code)

Max Activating Token Index: 99

Text #17

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2322. Min Act: -0.0001

Data Index: 299813 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2411. Min Act: -0.0001

Data Index: 1434962 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2407. Min Act: -0.0001

Data Index: 992108 (C4 (Web Text))

Max Activating Token Index: 659