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

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

Neuron 3716 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.5188. Min Act: -0.0000

Data Index: 1313957 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.3873. Min Act: -0.0000

Data Index: 1342314 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.3523. Min Act: -0.0000

Data Index: 589309 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.3464. Min Act: -0.0000

Data Index: 375897 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.3430. Min Act: -0.0000

Data Index: 252182 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.2490. Min Act: -0.0000

Data Index: 1262526 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.2343. Min Act: -0.0000

Data Index: 757110 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.2937. Min Act: -0.0000

Data Index: 1252294 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.2928. Min Act: -0.0000

Data Index: 884267 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.2811. Min Act: -0.0000

Data Index: 1086661 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.3548. Min Act: -0.0000

Data Index: 514808 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.2378. Min Act: -0.0000

Data Index: 591656 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.2431. Min Act: -0.0000

Data Index: 1338226 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.2433. Min Act: -0.0000

Data Index: 889733 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.1848. Min Act: -0.0000

Data Index: 833901 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.2526. Min Act: -0.0000

Data Index: 1006446 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.1805. Min Act: -0.0000

Data Index: 49919 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.1622. Min Act: -0.0000

Data Index: 859016 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.1368. Min Act: -0.0000

Data Index: 580270 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 1.5188. Min Range: -1.5188

Max Act: 1.1298. Min Act: -0.0000

Data Index: 515984 (C4 (Web Text))

Max Activating Token Index: 1017