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

Dataset: The Pile

Neuron 4518 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.6278. Min Act: -0.0000

Data Index: 353148 (The Pile)

Max Activating Token Index: 828

Text #1

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.3224. Min Act: -0.0000

Data Index: 409739 (The Pile)

Max Activating Token Index: 127

Text #2

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.2843. Min Act: -0.0000

Data Index: 475347 (The Pile)

Max Activating Token Index: 650

Text #3

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.3435. Min Act: -0.0000

Data Index: 1600614 (The Pile)

Max Activating Token Index: 616

Text #4

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.3236. Min Act: -0.0000

Data Index: 505096 (The Pile)

Max Activating Token Index: 180

Text #5

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.2369. Min Act: -0.0000

Data Index: 504179 (The Pile)

Max Activating Token Index: 535

Text #6

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.2068. Min Act: -0.0000

Data Index: 946952 (The Pile)

Max Activating Token Index: 312

Text #7

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.1834. Min Act: -0.0000

Data Index: 1775949 (The Pile)

Max Activating Token Index: 309

Text #8

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.1557. Min Act: -0.0000

Data Index: 1755511 (The Pile)

Max Activating Token Index: 414

Text #9

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.1550. Min Act: -0.0000

Data Index: 1453080 (The Pile)

Max Activating Token Index: 601

Text #10

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.0817. Min Act: -0.0000

Data Index: 686243 (The Pile)

Max Activating Token Index: 95

Text #11

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.1377. Min Act: -0.0000

Data Index: 361439 (The Pile)

Max Activating Token Index: 824

Text #12

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.1232. Min Act: -0.0000

Data Index: 180113 (The Pile)

Max Activating Token Index: 631

Text #13

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.1862. Min Act: -0.0000

Data Index: 385009 (The Pile)

Max Activating Token Index: 985

Text #14

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.0974. Min Act: -0.0000

Data Index: 1241185 (The Pile)

Max Activating Token Index: 978

Text #15

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.0357. Min Act: -0.0000

Data Index: 1250113 (The Pile)

Max Activating Token Index: 917

Text #16

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.0974. Min Act: -0.0000

Data Index: 1482320 (The Pile)

Max Activating Token Index: 296

Text #17

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.0820. Min Act: -0.0000

Data Index: 661329 (The Pile)

Max Activating Token Index: 277

Text #18

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.0688. Min Act: -0.0000

Data Index: 1519711 (The Pile)

Max Activating Token Index: 395

Text #19

Max Range: 1.6278. Min Range: -1.6278

Max Act: 1.0656. Min Act: -0.0000

Data Index: 959629 (The Pile)

Max Activating Token Index: 643