Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3883 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0329. Min Act: -0.0000

Data Index: 1613488 (The Pile)

Max Activating Token Index: 775

Text #1

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0325. Min Act: -0.0000

Data Index: 658388 (The Pile)

Max Activating Token Index: 14

Text #2

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0325. Min Act: -0.0000

Data Index: 1699865 (The Pile)

Max Activating Token Index: 88

Text #3

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0320. Min Act: -0.0000

Data Index: 1776579 (The Pile)

Max Activating Token Index: 764

Text #4

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0320. Min Act: -0.0000

Data Index: 827419 (The Pile)

Max Activating Token Index: 549

Text #5

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0315. Min Act: -0.0000

Data Index: 1190188 (The Pile)

Max Activating Token Index: 639

Text #6

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0315. Min Act: -0.0000

Data Index: 117459 (The Pile)

Max Activating Token Index: 912

Text #7

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0313. Min Act: -0.0000

Data Index: 1741858 (The Pile)

Max Activating Token Index: 305

Text #8

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0311. Min Act: -0.0000

Data Index: 46687 (The Pile)

Max Activating Token Index: 98

Text #9

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0312. Min Act: -0.0000

Data Index: 1658769 (The Pile)

Max Activating Token Index: 741

Text #10

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0309. Min Act: -0.0000

Data Index: 25166 (The Pile)

Max Activating Token Index: 166

Text #11

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0298. Min Act: -0.0000

Data Index: 304435 (The Pile)

Max Activating Token Index: 815

Text #12

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0298. Min Act: -0.0000

Data Index: 296716 (The Pile)

Max Activating Token Index: 906

Text #13

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0306. Min Act: -0.0000

Data Index: 1472218 (The Pile)

Max Activating Token Index: 497

Text #14

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0296. Min Act: -0.0000

Data Index: 1118082 (The Pile)

Max Activating Token Index: 98

Text #15

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0317. Min Act: -0.0000

Data Index: 1966178 (The Pile)

Max Activating Token Index: 98

Text #16

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0303. Min Act: -0.0000

Data Index: 1903863 (The Pile)

Max Activating Token Index: 763

Text #17

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0305. Min Act: -0.0000

Data Index: 24379 (The Pile)

Max Activating Token Index: 303

Text #18

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0303. Min Act: -0.0000

Data Index: 1196752 (The Pile)

Max Activating Token Index: 375

Text #19

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0303. Min Act: -0.0000

Data Index: 1467644 (The Pile)

Max Activating Token Index: 497