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

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

Neuron 4723 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: 2.6215. Min Range: -2.6215

Max Act: 2.6215. Min Act: -0.0000

Data Index: 941430 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 2.6215. Min Range: -2.6215

Max Act: 1.8857. Min Act: -0.0000

Data Index: 1072264 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 2.6215. Min Range: -2.6215

Max Act: 1.9887. Min Act: -0.0000

Data Index: 1040048 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 2.6215. Min Range: -2.6215

Max Act: 1.8422. Min Act: -0.0000

Data Index: 127302 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 2.6215. Min Range: -2.6215

Max Act: 1.7416. Min Act: -0.0000

Data Index: 1041439 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 2.6215. Min Range: -2.6215

Max Act: 1.6634. Min Act: -0.0000

Data Index: 1193968 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 2.6215. Min Range: -2.6215

Max Act: 1.5816. Min Act: -0.0000

Data Index: 334477 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 2.6215. Min Range: -2.6215

Max Act: 1.4206. Min Act: -0.0000

Data Index: 319386 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 2.6215. Min Range: -2.6215

Max Act: 1.2310. Min Act: -0.0000

Data Index: 1420031 (Python Code)

Max Activating Token Index: 559

Text #9

Max Range: 2.6215. Min Range: -2.6215

Max Act: 1.1223. Min Act: -0.0000

Data Index: 1513489 (Python Code)

Max Activating Token Index: 255

Text #10

Max Range: 2.6215. Min Range: -2.6215

Max Act: 1.3473. Min Act: -0.0000

Data Index: 1449299 (Python Code)

Max Activating Token Index: 79

Text #11

Max Range: 2.6215. Min Range: -2.6215

Max Act: 1.2414. Min Act: -0.0000

Data Index: 1382752 (Python Code)

Max Activating Token Index: 342

Text #12

Max Range: 2.6215. Min Range: -2.6215

Max Act: 1.3146. Min Act: -0.0000

Data Index: 978715 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 2.6215. Min Range: -2.6215

Max Act: 1.2469. Min Act: -0.0000

Data Index: 1598569 (Python Code)

Max Activating Token Index: 477

Text #14

Max Range: 2.6215. Min Range: -2.6215

Max Act: 1.2273. Min Act: -0.0000

Data Index: 1618472 (Python Code)

Max Activating Token Index: 667

Text #15

Max Range: 2.6215. Min Range: -2.6215

Max Act: 1.2627. Min Act: -0.0000

Data Index: 1624745 (Python Code)

Max Activating Token Index: 601

Text #16

Max Range: 2.6215. Min Range: -2.6215

Max Act: 1.1788. Min Act: -0.0000

Data Index: 902251 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 2.6215. Min Range: -2.6215

Max Act: 1.2362. Min Act: -0.0000

Data Index: 1455483 (Python Code)

Max Activating Token Index: 483

Text #18

Max Range: 2.6215. Min Range: -2.6215

Max Act: 1.1408. Min Act: -0.0000

Data Index: 1477587 (Python Code)

Max Activating Token Index: 197

Text #19

Max Range: 2.6215. Min Range: -2.6215

Max Act: 1.1452. Min Act: -0.0000

Data Index: 1612114 (Python Code)

Max Activating Token Index: 239