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

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

Neuron 442 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.3648. Min Act: -0.0000

Data Index: 356962 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.2749. Min Act: -0.0000

Data Index: 772515 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.2738. Min Act: -0.0000

Data Index: 100454 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.2443. Min Act: -0.0000

Data Index: 694174 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.2516. Min Act: -0.0000

Data Index: 717924 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.2389. Min Act: -0.0000

Data Index: 887648 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1355140 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.2195. Min Act: -0.0000

Data Index: 351798 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.2415. Min Act: -0.0000

Data Index: 703035 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.2214. Min Act: -0.0001

Data Index: 589637 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.2302. Min Act: -0.0000

Data Index: 351650 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1358308 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.2189. Min Act: -0.0000

Data Index: 974584 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.2281. Min Act: -0.0000

Data Index: 892552 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.2086. Min Act: -0.0000

Data Index: 355960 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.2071. Min Act: -0.0000

Data Index: 223753 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.1971. Min Act: -0.0000

Data Index: 339026 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.2089. Min Act: -0.0000

Data Index: 1042489 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.2034. Min Act: -0.0000

Data Index: 450930 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.3648. Min Range: -0.3648

Max Act: 0.1940. Min Act: -0.0001

Data Index: 1079595 (C4 (Web Text))

Max Activating Token Index: 99