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

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

Neuron 1327 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2872. Min Act: -0.0000

Data Index: 649615 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.3111. Min Act: -0.0000

Data Index: 1452885 (Python Code)

Max Activating Token Index: 155

Text #2

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2604. Min Act: -0.0000

Data Index: 1540144 (Python Code)

Max Activating Token Index: 400

Text #3

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1618012 (Python Code)

Max Activating Token Index: 185

Text #4

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1382098 (Python Code)

Max Activating Token Index: 985

Text #5

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1439990 (Python Code)

Max Activating Token Index: 722

Text #6

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2574. Min Act: -0.0000

Data Index: 1430578 (Python Code)

Max Activating Token Index: 725

Text #7

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2961. Min Act: -0.0000

Data Index: 1568073 (Python Code)

Max Activating Token Index: 112

Text #8

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2419. Min Act: -0.0000

Data Index: 1419113 (Python Code)

Max Activating Token Index: 282

Text #9

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1430795 (Python Code)

Max Activating Token Index: 236

Text #10

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1527558 (Python Code)

Max Activating Token Index: 560

Text #11

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1453165 (Python Code)

Max Activating Token Index: 501

Text #12

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1443286 (Python Code)

Max Activating Token Index: 236

Text #13

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1555433 (Python Code)

Max Activating Token Index: 664

Text #14

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1528607 (Python Code)

Max Activating Token Index: 122

Text #15

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1361142 (Python Code)

Max Activating Token Index: 190

Text #16

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2407. Min Act: -0.0000

Data Index: 1401973 (Python Code)

Max Activating Token Index: 391

Text #17

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1403044 (Python Code)

Max Activating Token Index: 175

Text #18

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2417. Min Act: -0.0000

Data Index: 541990 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2250. Min Act: -0.0000

Data Index: 1603663 (Python Code)

Max Activating Token Index: 267