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

Dataset: The Pile

Neuron 5075 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.6427. Min Act: -0.0000

Data Index: 1807505 (The Pile)

Max Activating Token Index: 777

Text #1

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.2666. Min Act: -0.0000

Data Index: 1824605 (The Pile)

Max Activating Token Index: 835

Text #2

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.1065. Min Act: -0.0000

Data Index: 776161 (The Pile)

Max Activating Token Index: 742

Text #3

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.0598. Min Act: -0.0000

Data Index: 1589437 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 1.6427. Min Range: -1.6427

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1669704 (The Pile)

Max Activating Token Index: 359

Text #5

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.0119. Min Act: -0.0000

Data Index: 1901598 (The Pile)

Max Activating Token Index: 896

Text #6

Max Range: 1.6427. Min Range: -1.6427

Max Act: 0.8415. Min Act: -0.0000

Data Index: 458299 (The Pile)

Max Activating Token Index: 957

Text #7

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.0159. Min Act: -0.0000

Data Index: 1216207 (The Pile)

Max Activating Token Index: 663

Text #8

Max Range: 1.6427. Min Range: -1.6427

Max Act: 0.8993. Min Act: -0.0000

Data Index: 881509 (The Pile)

Max Activating Token Index: 712

Text #9

Max Range: 1.6427. Min Range: -1.6427

Max Act: 0.8555. Min Act: -0.0000

Data Index: 1979502 (The Pile)

Max Activating Token Index: 890

Text #10

Max Range: 1.6427. Min Range: -1.6427

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1123617 (The Pile)

Max Activating Token Index: 350

Text #11

Max Range: 1.6427. Min Range: -1.6427

Max Act: 0.8385. Min Act: -0.0000

Data Index: 537899 (The Pile)

Max Activating Token Index: 952

Text #12

Max Range: 1.6427. Min Range: -1.6427

Max Act: 0.8514. Min Act: -0.0000

Data Index: 911411 (The Pile)

Max Activating Token Index: 705

Text #13

Max Range: 1.6427. Min Range: -1.6427

Max Act: 0.8157. Min Act: -0.0000

Data Index: 1598644 (The Pile)

Max Activating Token Index: 585

Text #14

Max Range: 1.6427. Min Range: -1.6427

Max Act: 0.8191. Min Act: -0.0000

Data Index: 864283 (The Pile)

Max Activating Token Index: 463

Text #15

Max Range: 1.6427. Min Range: -1.6427

Max Act: 0.8337. Min Act: -0.0000

Data Index: 1514995 (The Pile)

Max Activating Token Index: 975

Text #16

Max Range: 1.6427. Min Range: -1.6427

Max Act: 0.7803. Min Act: -0.0000

Data Index: 107009 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 1.6427. Min Range: -1.6427

Max Act: 0.7615. Min Act: -0.0000

Data Index: 1755235 (The Pile)

Max Activating Token Index: 941

Text #18

Max Range: 1.6427. Min Range: -1.6427

Max Act: 0.8787. Min Act: -0.0001

Data Index: 1782177 (The Pile)

Max Activating Token Index: 700

Text #19

Max Range: 1.6427. Min Range: -1.6427

Max Act: 0.8008. Min Act: -0.0000

Data Index: 2923 (The Pile)

Max Activating Token Index: 614