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

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

Neuron 3877 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8905. Min Range: -2.8905

Max Act: 2.8905. Min Act: -0.0000

Data Index: 979769 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 2.8905. Min Range: -2.8905

Max Act: 2.1335. Min Act: -0.0000

Data Index: 432636 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 2.8905. Min Range: -2.8905

Max Act: 2.2313. Min Act: -0.0000

Data Index: 469399 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 2.8905. Min Range: -2.8905

Max Act: 2.1684. Min Act: -0.0000

Data Index: 686211 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 2.8905. Min Range: -2.8905

Max Act: 2.1307. Min Act: -0.0000

Data Index: 454925 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 2.8905. Min Range: -2.8905

Max Act: 2.1375. Min Act: -0.0000

Data Index: 564818 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 2.8905. Min Range: -2.8905

Max Act: 1.9146. Min Act: -0.0000

Data Index: 476697 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 2.8905. Min Range: -2.8905

Max Act: 2.0345. Min Act: -0.0000

Data Index: 201746 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 2.8905. Min Range: -2.8905

Max Act: 2.1198. Min Act: -0.0000

Data Index: 318755 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 2.8905. Min Range: -2.8905

Max Act: 1.8893. Min Act: -0.0000

Data Index: 1254981 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 2.8905. Min Range: -2.8905

Max Act: 1.9523. Min Act: -0.0000

Data Index: 636975 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 2.8905. Min Range: -2.8905

Max Act: 1.9184. Min Act: -0.0000

Data Index: 648061 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 2.8905. Min Range: -2.8905

Max Act: 1.8995. Min Act: -0.0000

Data Index: 19728 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 2.8905. Min Range: -2.8905

Max Act: 1.8528. Min Act: -0.0000

Data Index: 235487 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 2.8905. Min Range: -2.8905

Max Act: 1.8342. Min Act: -0.0000

Data Index: 333239 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 2.8905. Min Range: -2.8905

Max Act: 1.9292. Min Act: -0.0000

Data Index: 508293 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 2.8905. Min Range: -2.8905

Max Act: 1.7264. Min Act: -0.0000

Data Index: 631344 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 2.8905. Min Range: -2.8905

Max Act: 1.8204. Min Act: -0.0000

Data Index: 1067891 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 2.8905. Min Range: -2.8905

Max Act: 1.7769. Min Act: -0.0000

Data Index: 1261864 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 2.8905. Min Range: -2.8905

Max Act: 1.7434. Min Act: -0.0000

Data Index: 91106 (C4 (Web Text))

Max Activating Token Index: 752