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

Dataset: The Pile

Neuron 1703 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: 0.0382. Min Range: -0.0382

Max Act: 0.0382. Min Act: -0.0000

Data Index: 1064963 (The Pile)

Max Activating Token Index: 3

Text #1

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0312. Min Act: -0.0000

Data Index: 1523808 (The Pile)

Max Activating Token Index: 4

Text #2

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0246. Min Act: -0.0000

Data Index: 1078589 (The Pile)

Max Activating Token Index: 4

Text #3

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0238. Min Act: -0.0000

Data Index: 1007822 (The Pile)

Max Activating Token Index: 4

Text #4

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0236. Min Act: -0.0000

Data Index: 1472230 (The Pile)

Max Activating Token Index: 3

Text #5

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0233. Min Act: -0.0000

Data Index: 1562256 (The Pile)

Max Activating Token Index: 3

Text #6

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0226. Min Act: -0.0000

Data Index: 1360523 (The Pile)

Max Activating Token Index: 3

Text #7

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0230. Min Act: -0.0000

Data Index: 198367 (The Pile)

Max Activating Token Index: 6

Text #8

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0219. Min Act: -0.0000

Data Index: 808772 (The Pile)

Max Activating Token Index: 3

Text #9

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0218. Min Act: -0.0000

Data Index: 809692 (The Pile)

Max Activating Token Index: 4

Text #10

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0215. Min Act: -0.0000

Data Index: 260751 (The Pile)

Max Activating Token Index: 3

Text #11

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0214. Min Act: -0.0000

Data Index: 1602569 (The Pile)

Max Activating Token Index: 8

Text #12

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0213. Min Act: -0.0000

Data Index: 1930469 (The Pile)

Max Activating Token Index: 5

Text #13

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0212. Min Act: -0.0000

Data Index: 257001 (The Pile)

Max Activating Token Index: 7

Text #14

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0210. Min Act: -0.0000

Data Index: 304805 (The Pile)

Max Activating Token Index: 3

Text #15

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0209. Min Act: -0.0000

Data Index: 535477 (The Pile)

Max Activating Token Index: 3

Text #16

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0207. Min Act: -0.0000

Data Index: 1630224 (The Pile)

Max Activating Token Index: 5

Text #17

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0206. Min Act: -0.0000

Data Index: 158756 (The Pile)

Max Activating Token Index: 4

Text #18

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0206. Min Act: -0.0000

Data Index: 1152958 (The Pile)

Max Activating Token Index: 6

Text #19

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0201. Min Act: -0.0000

Data Index: 1821600 (The Pile)

Max Activating Token Index: 5