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

Dataset: The Pile

Neuron 2424 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5234. Min Range: -3.5234

Max Act: 3.5234. Min Act: -0.0000

Data Index: 1079040 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 3.5234. Min Range: -3.5234

Max Act: 3.1362. Min Act: -0.0000

Data Index: 159437 (The Pile)

Max Activating Token Index: 622

Text #2

Max Range: 3.5234. Min Range: -3.5234

Max Act: 3.4316. Min Act: -0.0000

Data Index: 911903 (The Pile)

Max Activating Token Index: 400

Text #3

Max Range: 3.5234. Min Range: -3.5234

Max Act: 2.9584. Min Act: -0.0000

Data Index: 1171963 (The Pile)

Max Activating Token Index: 289

Text #4

Max Range: 3.5234. Min Range: -3.5234

Max Act: 3.0348. Min Act: -0.0000

Data Index: 1976601 (The Pile)

Max Activating Token Index: 160

Text #5

Max Range: 3.5234. Min Range: -3.5234

Max Act: 3.1629. Min Act: -0.0000

Data Index: 1075563 (The Pile)

Max Activating Token Index: 946

Text #6

Max Range: 3.5234. Min Range: -3.5234

Max Act: 2.9741. Min Act: -0.0000

Data Index: 1678594 (The Pile)

Max Activating Token Index: 1010

Text #7

Max Range: 3.5234. Min Range: -3.5234

Max Act: 2.9439. Min Act: -0.0000

Data Index: 1419649 (The Pile)

Max Activating Token Index: 312

Text #8

Max Range: 3.5234. Min Range: -3.5234

Max Act: 2.9008. Min Act: -0.0000

Data Index: 741578 (The Pile)

Max Activating Token Index: 768

Text #9

Max Range: 3.5234. Min Range: -3.5234

Max Act: 2.7538. Min Act: -0.0000

Data Index: 1794649 (The Pile)

Max Activating Token Index: 520

Text #10

Max Range: 3.5234. Min Range: -3.5234

Max Act: 2.8662. Min Act: -0.0000

Data Index: 1813015 (The Pile)

Max Activating Token Index: 99

Text #11

Max Range: 3.5234. Min Range: -3.5234

Max Act: 2.7016. Min Act: -0.0000

Data Index: 911811 (The Pile)

Max Activating Token Index: 34

Text #12

Max Range: 3.5234. Min Range: -3.5234

Max Act: 2.7586. Min Act: -0.0000

Data Index: 682299 (The Pile)

Max Activating Token Index: 741

Text #13

Max Range: 3.5234. Min Range: -3.5234

Max Act: 2.7518. Min Act: -0.0000

Data Index: 1817908 (The Pile)

Max Activating Token Index: 59

Text #14

Max Range: 3.5234. Min Range: -3.5234

Max Act: 2.7271. Min Act: -0.0000

Data Index: 1234967 (The Pile)

Max Activating Token Index: 71

Text #15

Max Range: 3.5234. Min Range: -3.5234

Max Act: 2.5645. Min Act: -0.0000

Data Index: 1440337 (The Pile)

Max Activating Token Index: 904

Text #16

Max Range: 3.5234. Min Range: -3.5234

Max Act: 2.5417. Min Act: -0.0000

Data Index: 309738 (The Pile)

Max Activating Token Index: 892

Text #17

Max Range: 3.5234. Min Range: -3.5234

Max Act: 2.5391. Min Act: -0.0000

Data Index: 1867092 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 3.5234. Min Range: -3.5234

Max Act: 2.6304. Min Act: -0.0000

Data Index: 435726 (The Pile)

Max Activating Token Index: 175

Text #19

Max Range: 3.5234. Min Range: -3.5234

Max Act: 2.4961. Min Act: -0.0000

Data Index: 1402711 (The Pile)

Max Activating Token Index: 453