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

Dataset: The Pile

Neuron 3616 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: 1.4398. Min Range: -1.4398

Max Act: 1.4398. Min Act: -0.0000

Data Index: 47765 (The Pile)

Max Activating Token Index: 78

Text #1

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.4205. Min Act: -0.0000

Data Index: 1837036 (The Pile)

Max Activating Token Index: 521

Text #2

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.2780. Min Act: -0.0000

Data Index: 804058 (The Pile)

Max Activating Token Index: 37

Text #3

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.0609. Min Act: -0.0000

Data Index: 393317 (The Pile)

Max Activating Token Index: 195

Text #4

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.1663. Min Act: -0.0000

Data Index: 340204 (The Pile)

Max Activating Token Index: 423

Text #5

Max Range: 1.4398. Min Range: -1.4398

Max Act: 0.9596. Min Act: -0.0000

Data Index: 1823151 (The Pile)

Max Activating Token Index: 35

Text #6

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.0841. Min Act: -0.0000

Data Index: 666175 (The Pile)

Max Activating Token Index: 308

Text #7

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.0189. Min Act: -0.0000

Data Index: 1408563 (The Pile)

Max Activating Token Index: 240

Text #8

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.0599. Min Act: -0.0000

Data Index: 1668221 (The Pile)

Max Activating Token Index: 676

Text #9

Max Range: 1.4398. Min Range: -1.4398

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1685422 (The Pile)

Max Activating Token Index: 940

Text #10

Max Range: 1.4398. Min Range: -1.4398

Max Act: 0.9680. Min Act: -0.0000

Data Index: 129358 (The Pile)

Max Activating Token Index: 248

Text #11

Max Range: 1.4398. Min Range: -1.4398

Max Act: 0.9629. Min Act: -0.0000

Data Index: 331870 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.0655. Min Act: -0.0000

Data Index: 1916459 (The Pile)

Max Activating Token Index: 595

Text #13

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.0243. Min Act: -0.0000

Data Index: 270260 (The Pile)

Max Activating Token Index: 503

Text #14

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.0257. Min Act: -0.0000

Data Index: 1457230 (The Pile)

Max Activating Token Index: 66

Text #15

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1566362 (The Pile)

Max Activating Token Index: 832

Text #16

Max Range: 1.4398. Min Range: -1.4398

Max Act: 0.9474. Min Act: -0.0000

Data Index: 1557189 (The Pile)

Max Activating Token Index: 630

Text #17

Max Range: 1.4398. Min Range: -1.4398

Max Act: 0.9701. Min Act: -0.0000

Data Index: 988315 (The Pile)

Max Activating Token Index: 1004

Text #18

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.0286. Min Act: -0.0000

Data Index: 1911347 (The Pile)

Max Activating Token Index: 810

Text #19

Max Range: 1.4398. Min Range: -1.4398

Max Act: 0.9998. Min Act: -0.0000

Data Index: 223754 (The Pile)

Max Activating Token Index: 138