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

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

Neuron 1542 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: 0.4445. Min Range: -0.4445

Max Act: 0.4445. Min Act: -0.0000

Data Index: 1653100 (Python Code)

Max Activating Token Index: 393

Text #1

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.4114. Min Act: -0.0000

Data Index: 547464 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1591287 (Python Code)

Max Activating Token Index: 145

Text #3

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1505028 (Python Code)

Max Activating Token Index: 592

Text #4

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3428. Min Act: -0.0000

Data Index: 1647894 (Python Code)

Max Activating Token Index: 305

Text #5

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3091. Min Act: -0.0000

Data Index: 1411373 (Python Code)

Max Activating Token Index: 565

Text #6

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3453. Min Act: -0.0000

Data Index: 1527886 (Python Code)

Max Activating Token Index: 442

Text #7

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3188. Min Act: -0.0000

Data Index: 1095309 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1652340 (Python Code)

Max Activating Token Index: 212

Text #9

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3144. Min Act: -0.0000

Data Index: 482939 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3108. Min Act: -0.0000

Data Index: 1476097 (Python Code)

Max Activating Token Index: 536

Text #11

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.2926. Min Act: -0.0000

Data Index: 1540320 (Python Code)

Max Activating Token Index: 1001

Text #12

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.2944. Min Act: -0.0000

Data Index: 648600 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1534283 (Python Code)

Max Activating Token Index: 478

Text #14

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3167. Min Act: -0.0000

Data Index: 1648462 (Python Code)

Max Activating Token Index: 373

Text #15

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3112. Min Act: -0.0000

Data Index: 1580201 (Python Code)

Max Activating Token Index: 689

Text #16

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.2888. Min Act: -0.0000

Data Index: 88138 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.2925. Min Act: -0.0000

Data Index: 1525281 (Python Code)

Max Activating Token Index: 116

Text #18

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1395768 (Python Code)

Max Activating Token Index: 412

Text #19

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1476438 (Python Code)

Max Activating Token Index: 475