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

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

Neuron 295 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.7580. Min Act: -0.0000

Data Index: 546660 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1150754 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6320. Min Act: -0.0000

Data Index: 896563 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6123. Min Act: -0.0000

Data Index: 305838 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1259291 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6324. Min Act: -0.0000

Data Index: 123383 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5911. Min Act: -0.0000

Data Index: 529881 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1435782 (Python Code)

Max Activating Token Index: 215

Text #8

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1104872 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5380. Min Act: -0.0000

Data Index: 104022 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5504. Min Act: -0.0000

Data Index: 746798 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5467. Min Act: -0.0000

Data Index: 282368 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5496. Min Act: -0.0000

Data Index: 951832 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5077. Min Act: -0.0000

Data Index: 895551 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5527. Min Act: -0.0000

Data Index: 541020 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1311720 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5041. Min Act: -0.0000

Data Index: 220134 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.4986. Min Act: -0.0000

Data Index: 175928 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5236. Min Act: -0.0000

Data Index: 497114 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5205. Min Act: -0.0000

Data Index: 698197 (C4 (Web Text))

Max Activating Token Index: 465