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

Dataset: The Pile

Neuron 355 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: 5.0322. Min Range: -5.0322

Max Act: 4.8924. Min Act: -0.0000

Data Index: 1173867 (The Pile)

Max Activating Token Index: 583

Text #1

Max Range: 5.0322. Min Range: -5.0322

Max Act: 5.0322. Min Act: -0.0000

Data Index: 26351 (The Pile)

Max Activating Token Index: 692

Text #2

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.2344. Min Act: -0.0000

Data Index: 499355 (The Pile)

Max Activating Token Index: 786

Text #3

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.4234. Min Act: -0.0000

Data Index: 76426 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.3942. Min Act: -0.0000

Data Index: 1898767 (The Pile)

Max Activating Token Index: 697

Text #5

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.4572. Min Act: -0.0000

Data Index: 412573 (The Pile)

Max Activating Token Index: 606

Text #6

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.4106. Min Act: -0.0000

Data Index: 1529658 (The Pile)

Max Activating Token Index: 73

Text #7

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.2702. Min Act: -0.0000

Data Index: 607777 (The Pile)

Max Activating Token Index: 743

Text #8

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.1490. Min Act: -0.0000

Data Index: 24577 (The Pile)

Max Activating Token Index: 901

Text #9

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.2261. Min Act: -0.0000

Data Index: 170777 (The Pile)

Max Activating Token Index: 680

Text #10

Max Range: 5.0322. Min Range: -5.0322

Max Act: 3.7433. Min Act: -0.0000

Data Index: 1897095 (The Pile)

Max Activating Token Index: 1002

Text #11

Max Range: 5.0322. Min Range: -5.0322

Max Act: 3.8010. Min Act: -0.0000

Data Index: 1272378 (The Pile)

Max Activating Token Index: 449

Text #12

Max Range: 5.0322. Min Range: -5.0322

Max Act: 3.9112. Min Act: -0.0000

Data Index: 1352115 (The Pile)

Max Activating Token Index: 429

Text #13

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.0449. Min Act: -0.0000

Data Index: 36137 (The Pile)

Max Activating Token Index: 912

Text #14

Max Range: 5.0322. Min Range: -5.0322

Max Act: 3.8455. Min Act: -0.0000

Data Index: 1123481 (The Pile)

Max Activating Token Index: 388

Text #15

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.0071. Min Act: -0.0000

Data Index: 987710 (The Pile)

Max Activating Token Index: 910

Text #16

Max Range: 5.0322. Min Range: -5.0322

Max Act: 3.8201. Min Act: -0.0000

Data Index: 1453181 (The Pile)

Max Activating Token Index: 527

Text #17

Max Range: 5.0322. Min Range: -5.0322

Max Act: 3.8132. Min Act: -0.0000

Data Index: 975840 (The Pile)

Max Activating Token Index: 808

Text #18

Max Range: 5.0322. Min Range: -5.0322

Max Act: 3.9394. Min Act: -0.0000

Data Index: 1883290 (The Pile)

Max Activating Token Index: 577

Text #19

Max Range: 5.0322. Min Range: -5.0322

Max Act: 4.0775. Min Act: -0.0000

Data Index: 1633079 (The Pile)

Max Activating Token Index: 990