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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 273 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.5623. Min Act: 0.0000

Data Index: 621606 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.5516. Min Act: -0.0001

Data Index: 953854 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.5134. Min Act: -0.0001

Data Index: 697979 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4750. Min Act: -0.0000

Data Index: 175614 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4647. Min Act: -0.0000

Data Index: 285484 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4608. Min Act: -0.0000

Data Index: 863812 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4577. Min Act: -0.0001

Data Index: 503297 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4521. Min Act: -0.0000

Data Index: 551713 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4524. Min Act: -0.0000

Data Index: 14012 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4484. Min Act: -0.0001

Data Index: 826133 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4475. Min Act: -0.0001

Data Index: 27046 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4387. Min Act: -0.0001

Data Index: 287586 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1197703 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1141112 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4374. Min Act: -0.0000

Data Index: 139713 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4360. Min Act: -0.0000

Data Index: 693179 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4351. Min Act: -0.0000

Data Index: 612624 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4161. Min Act: -0.0000

Data Index: 33107 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4307. Min Act: -0.0000

Data Index: 1195322 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.3966. Min Act: -0.0000

Data Index: 403775 (C4 (Web Text))

Max Activating Token Index: 225