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

Dataset: The Pile

Neuron 2019 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.6098. Min Act: -0.0000

Data Index: 600416 (The Pile)

Max Activating Token Index: 932

Text #1

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1109090 (The Pile)

Max Activating Token Index: 592

Text #2

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1072626 (The Pile)

Max Activating Token Index: 605

Text #3

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.5522. Min Act: -0.0000

Data Index: 1378143 (The Pile)

Max Activating Token Index: 338

Text #4

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.5807. Min Act: -0.0000

Data Index: 1692639 (The Pile)

Max Activating Token Index: 725

Text #5

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.6304. Min Act: -0.0000

Data Index: 411529 (The Pile)

Max Activating Token Index: 823

Text #6

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.5689. Min Act: -0.0000

Data Index: 857603 (The Pile)

Max Activating Token Index: 610

Text #7

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.5454. Min Act: -0.0000

Data Index: 226247 (The Pile)

Max Activating Token Index: 581

Text #8

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1617672 (The Pile)

Max Activating Token Index: 258

Text #9

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.6174. Min Act: -0.0000

Data Index: 1292501 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1272671 (The Pile)

Max Activating Token Index: 635

Text #11

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1177311 (The Pile)

Max Activating Token Index: 83

Text #12

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1717405 (The Pile)

Max Activating Token Index: 332

Text #13

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4825. Min Act: -0.0000

Data Index: 14567 (The Pile)

Max Activating Token Index: 583

Text #14

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4996. Min Act: -0.0000

Data Index: 598505 (The Pile)

Max Activating Token Index: 859

Text #15

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4956. Min Act: -0.0000

Data Index: 499751 (The Pile)

Max Activating Token Index: 267

Text #16

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1028207 (The Pile)

Max Activating Token Index: 421

Text #17

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4615. Min Act: -0.0000

Data Index: 1933685 (The Pile)

Max Activating Token Index: 918

Text #18

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4290. Min Act: -0.0000

Data Index: 786416 (The Pile)

Max Activating Token Index: 580

Text #19

Max Range: 0.6409. Min Range: -0.6409

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1165761 (The Pile)

Max Activating Token Index: 1002