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

Dataset: The Pile

Neuron 3875 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: 0.0466. Min Range: -0.0466

Max Act: 0.0466. Min Act: -0.0000

Data Index: 1478666 (The Pile)

Max Activating Token Index: 833

Text #1

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0368. Min Act: -0.0000

Data Index: 1045855 (The Pile)

Max Activating Token Index: 928

Text #2

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0358. Min Act: -0.0000

Data Index: 1622547 (The Pile)

Max Activating Token Index: 376

Text #3

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0354. Min Act: 0.0000

Data Index: 1845578 (The Pile)

Max Activating Token Index: 315

Text #4

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0339. Min Act: -0.0000

Data Index: 364242 (The Pile)

Max Activating Token Index: 937

Text #5

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0349. Min Act: -0.0000

Data Index: 196621 (The Pile)

Max Activating Token Index: 1013

Text #6

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0345. Min Act: 0.0000

Data Index: 1418654 (The Pile)

Max Activating Token Index: 767

Text #7

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0332. Min Act: -0.0000

Data Index: 791158 (The Pile)

Max Activating Token Index: 612

Text #8

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0343. Min Act: -0.0000

Data Index: 1067332 (The Pile)

Max Activating Token Index: 1009

Text #9

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0328. Min Act: -0.0000

Data Index: 1512381 (The Pile)

Max Activating Token Index: 885

Text #10

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0327. Min Act: -0.0000

Data Index: 512828 (The Pile)

Max Activating Token Index: 555

Text #11

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0327. Min Act: 0.0000

Data Index: 714000 (The Pile)

Max Activating Token Index: 966

Text #12

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0323. Min Act: -0.0000

Data Index: 1210697 (The Pile)

Max Activating Token Index: 26

Text #13

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0321. Min Act: -0.0000

Data Index: 190940 (The Pile)

Max Activating Token Index: 683

Text #14

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0320. Min Act: -0.0000

Data Index: 654844 (The Pile)

Max Activating Token Index: 280

Text #15

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0318. Min Act: -0.0000

Data Index: 1814568 (The Pile)

Max Activating Token Index: 856

Text #16

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0317. Min Act: -0.0000

Data Index: 929819 (The Pile)

Max Activating Token Index: 630

Text #17

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0316. Min Act: -0.0000

Data Index: 1594830 (The Pile)

Max Activating Token Index: 114

Text #18

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0314. Min Act: 0.0000

Data Index: 544225 (The Pile)

Max Activating Token Index: 933

Text #19

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0312. Min Act: -0.0000

Data Index: 1396540 (The Pile)

Max Activating Token Index: 723