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

Dataset: The Pile

Neuron 841 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1391706 (The Pile)

Max Activating Token Index: 271

Text #1

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.4234. Min Act: -0.0000

Data Index: 233937 (The Pile)

Max Activating Token Index: 46

Text #2

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.3956. Min Act: -0.0000

Data Index: 188309 (The Pile)

Max Activating Token Index: 569

Text #3

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.3758. Min Act: 0.0000

Data Index: 1744486 (The Pile)

Max Activating Token Index: 900

Text #4

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.3228. Min Act: -0.0000

Data Index: 1608440 (The Pile)

Max Activating Token Index: 200

Text #5

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.3067. Min Act: -0.0000

Data Index: 497382 (The Pile)

Max Activating Token Index: 380

Text #6

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.2990. Min Act: -0.0000

Data Index: 421498 (The Pile)

Max Activating Token Index: 416

Text #7

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.2925. Min Act: -0.0000

Data Index: 1636168 (The Pile)

Max Activating Token Index: 132

Text #8

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.2828. Min Act: 0.0000

Data Index: 828422 (The Pile)

Max Activating Token Index: 886

Text #9

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.2639. Min Act: 0.0000

Data Index: 154851 (The Pile)

Max Activating Token Index: 345

Text #10

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.2817. Min Act: -0.0000

Data Index: 279474 (The Pile)

Max Activating Token Index: 989

Text #11

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.2750. Min Act: 0.0000

Data Index: 1627988 (The Pile)

Max Activating Token Index: 620

Text #12

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.2693. Min Act: -0.0000

Data Index: 527773 (The Pile)

Max Activating Token Index: 190

Text #13

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.2689. Min Act: 0.0000

Data Index: 623742 (The Pile)

Max Activating Token Index: 274

Text #14

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.2760. Min Act: -0.0000

Data Index: 361957 (The Pile)

Max Activating Token Index: 662

Text #15

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.2736. Min Act: -0.0000

Data Index: 276252 (The Pile)

Max Activating Token Index: 330

Text #16

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.2707. Min Act: -0.0000

Data Index: 249574 (The Pile)

Max Activating Token Index: 192

Text #17

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.2685. Min Act: -0.0000

Data Index: 405025 (The Pile)

Max Activating Token Index: 536

Text #18

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.2586. Min Act: -0.0000

Data Index: 904264 (The Pile)

Max Activating Token Index: 780

Text #19

Max Range: 0.4576. Min Range: -0.4576

Max Act: 0.2576. Min Act: -0.0000

Data Index: 1030620 (The Pile)

Max Activating Token Index: 176