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

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

Neuron 1164 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.2310. Min Act: -0.0000

Data Index: 1481577 (Python Code)

Max Activating Token Index: 149

Text #1

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.3216. Min Act: -0.0000

Data Index: 139325 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.0621. Min Act: -0.0000

Data Index: 634391 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.1870. Min Act: -0.0000

Data Index: 1366282 (Python Code)

Max Activating Token Index: 637

Text #4

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.1049. Min Act: -0.0000

Data Index: 1650331 (Python Code)

Max Activating Token Index: 552

Text #5

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.0684. Min Act: -0.0000

Data Index: 1467430 (Python Code)

Max Activating Token Index: 172

Text #6

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.1804. Min Act: -0.0000

Data Index: 498789 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.0957. Min Act: -0.0000

Data Index: 576440 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 2.3216. Min Range: -2.3216

Max Act: 1.9985. Min Act: -0.0001

Data Index: 1530476 (Python Code)

Max Activating Token Index: 336

Text #9

Max Range: 2.3216. Min Range: -2.3216

Max Act: 1.9859. Min Act: -0.0000

Data Index: 277733 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.0786. Min Act: -0.0000

Data Index: 1614140 (Python Code)

Max Activating Token Index: 695

Text #11

Max Range: 2.3216. Min Range: -2.3216

Max Act: 2.0524. Min Act: -0.0000

Data Index: 1399583 (Python Code)

Max Activating Token Index: 814

Text #12

Max Range: 2.3216. Min Range: -2.3216

Max Act: 1.9239. Min Act: -0.0000

Data Index: 1522335 (Python Code)

Max Activating Token Index: 797

Text #13

Max Range: 2.3216. Min Range: -2.3216

Max Act: 1.8796. Min Act: -0.0000

Data Index: 1653208 (Python Code)

Max Activating Token Index: 966

Text #14

Max Range: 2.3216. Min Range: -2.3216

Max Act: 1.8158. Min Act: -0.0000

Data Index: 348390 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 2.3216. Min Range: -2.3216

Max Act: 1.8545. Min Act: -0.0000

Data Index: 347088 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 2.3216. Min Range: -2.3216

Max Act: 1.8153. Min Act: -0.0000

Data Index: 622128 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 2.3216. Min Range: -2.3216

Max Act: 1.8707. Min Act: -0.0000

Data Index: 814794 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 2.3216. Min Range: -2.3216

Max Act: 1.8575. Min Act: -0.0000

Data Index: 1460162 (Python Code)

Max Activating Token Index: 334

Text #19

Max Range: 2.3216. Min Range: -2.3216

Max Act: 1.8757. Min Act: -0.0000

Data Index: 1542492 (Python Code)

Max Activating Token Index: 177