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

Dataset: The Pile

Neuron 800 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0306. Min Act: -0.0000

Data Index: 326076 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0306. Min Act: -0.0000

Data Index: 47902 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0301. Min Act: -0.0000

Data Index: 1501816 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0300. Min Act: -0.0000

Data Index: 371243 (The Pile)

Max Activating Token Index: 3

Text #4

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0310. Min Act: -0.0000

Data Index: 1435571 (The Pile)

Max Activating Token Index: 2

Text #5

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0298. Min Act: -0.0000

Data Index: 447059 (The Pile)

Max Activating Token Index: 2

Text #6

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0298. Min Act: -0.0000

Data Index: 1961393 (The Pile)

Max Activating Token Index: 2

Text #7

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0298. Min Act: -0.0000

Data Index: 1532943 (The Pile)

Max Activating Token Index: 2

Text #8

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0297. Min Act: -0.0000

Data Index: 1330285 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0296. Min Act: -0.0000

Data Index: 719682 (The Pile)

Max Activating Token Index: 17

Text #10

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0307. Min Act: -0.0000

Data Index: 189592 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0296. Min Act: -0.0000

Data Index: 1304194 (The Pile)

Max Activating Token Index: 3

Text #12

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0296. Min Act: -0.0000

Data Index: 699252 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0295. Min Act: -0.0000

Data Index: 925175 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0294. Min Act: -0.0000

Data Index: 1238445 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0304. Min Act: -0.0000

Data Index: 1448082 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0290. Min Act: -0.0000

Data Index: 1535727 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0291. Min Act: -0.0000

Data Index: 661268 (The Pile)

Max Activating Token Index: 148

Text #18

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0290. Min Act: -0.0000

Data Index: 337471 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0290. Min Act: -0.0000

Data Index: 1659744 (The Pile)

Max Activating Token Index: 1023