Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 669 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.4372. Min Act: -0.0000

Data Index: 133643 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.3880. Min Act: -0.0000

Data Index: 386527 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.3622. Min Act: -0.0000

Data Index: 773023 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.2923. Min Act: -0.0000

Data Index: 819437 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.2919. Min Act: -0.0000

Data Index: 926127 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.2670. Min Act: -0.0000

Data Index: 402858 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.2930. Min Act: -0.0000

Data Index: 596434 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1469830 (Python Code)

Max Activating Token Index: 775

Text #8

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.2729. Min Act: -0.0000

Data Index: 976843 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.2494. Min Act: -0.0000

Data Index: 23773 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.2614. Min Act: -0.0000

Data Index: 999619 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1337362 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.2554. Min Act: -0.0000

Data Index: 183084 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.2448. Min Act: -0.0000

Data Index: 811884 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.2379. Min Act: -0.0000

Data Index: 1373409 (Python Code)

Max Activating Token Index: 179

Text #15

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.2294. Min Act: -0.0000

Data Index: 460347 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.2341. Min Act: -0.0000

Data Index: 154164 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.2261. Min Act: -0.0000

Data Index: 769392 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.2185. Min Act: -0.0000

Data Index: 226634 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1167861 (C4 (Web Text))

Max Activating Token Index: 373