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

Dataset: The Pile

Neuron 3056 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: 3.2588. Min Range: -3.2588

Max Act: 3.2588. Min Act: -0.0000

Data Index: 398134 (The Pile)

Max Activating Token Index: 628

Text #1

Max Range: 3.2588. Min Range: -3.2588

Max Act: 2.8626. Min Act: -0.0000

Data Index: 1202267 (The Pile)

Max Activating Token Index: 961

Text #2

Max Range: 3.2588. Min Range: -3.2588

Max Act: 2.8292. Min Act: -0.0000

Data Index: 144833 (The Pile)

Max Activating Token Index: 652

Text #3

Max Range: 3.2588. Min Range: -3.2588

Max Act: 2.8198. Min Act: -0.0000

Data Index: 1943227 (The Pile)

Max Activating Token Index: 823

Text #4

Max Range: 3.2588. Min Range: -3.2588

Max Act: 2.5415. Min Act: -0.0000

Data Index: 457566 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 3.2588. Min Range: -3.2588

Max Act: 2.7981. Min Act: -0.0000

Data Index: 1132778 (The Pile)

Max Activating Token Index: 580

Text #6

Max Range: 3.2588. Min Range: -3.2588

Max Act: 2.5275. Min Act: -0.0000

Data Index: 1305176 (The Pile)

Max Activating Token Index: 324

Text #7

Max Range: 3.2588. Min Range: -3.2588

Max Act: 2.4930. Min Act: -0.0000

Data Index: 1624860 (The Pile)

Max Activating Token Index: 1021

Text #8

Max Range: 3.2588. Min Range: -3.2588

Max Act: 2.3421. Min Act: -0.0000

Data Index: 1284582 (The Pile)

Max Activating Token Index: 979

Text #9

Max Range: 3.2588. Min Range: -3.2588

Max Act: 2.6877. Min Act: -0.0000

Data Index: 21481 (The Pile)

Max Activating Token Index: 496

Text #10

Max Range: 3.2588. Min Range: -3.2588

Max Act: 2.5725. Min Act: -0.0000

Data Index: 1042149 (The Pile)

Max Activating Token Index: 590

Text #11

Max Range: 3.2588. Min Range: -3.2588

Max Act: 2.6805. Min Act: -0.0000

Data Index: 671401 (The Pile)

Max Activating Token Index: 672

Text #12

Max Range: 3.2588. Min Range: -3.2588

Max Act: 2.6726. Min Act: -0.0000

Data Index: 1448825 (The Pile)

Max Activating Token Index: 664

Text #13

Max Range: 3.2588. Min Range: -3.2588

Max Act: 2.6044. Min Act: -0.0000

Data Index: 1139028 (The Pile)

Max Activating Token Index: 922

Text #14

Max Range: 3.2588. Min Range: -3.2588

Max Act: 2.4022. Min Act: -0.0000

Data Index: 333816 (The Pile)

Max Activating Token Index: 332

Text #15

Max Range: 3.2588. Min Range: -3.2588

Max Act: 2.5062. Min Act: -0.0000

Data Index: 287838 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 3.2588. Min Range: -3.2588

Max Act: 2.3494. Min Act: -0.0000

Data Index: 979805 (The Pile)

Max Activating Token Index: 527

Text #17

Max Range: 3.2588. Min Range: -3.2588

Max Act: 2.5596. Min Act: -0.0000

Data Index: 1022121 (The Pile)

Max Activating Token Index: 823

Text #18

Max Range: 3.2588. Min Range: -3.2588

Max Act: 2.2916. Min Act: -0.0000

Data Index: 1554125 (The Pile)

Max Activating Token Index: 490

Text #19

Max Range: 3.2588. Min Range: -3.2588

Max Act: 2.2827. Min Act: -0.0000

Data Index: 1677015 (The Pile)

Max Activating Token Index: 666