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

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

Neuron 1517 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7623. Min Act: -0.0001

Data Index: 429473 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7660. Min Act: -0.0001

Data Index: 1115217 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7376. Min Act: -0.0001

Data Index: 347140 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7629. Min Act: -0.0001

Data Index: 1291852 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7491. Min Act: -0.0001

Data Index: 771296 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6530. Min Act: -0.0001

Data Index: 59522 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6697. Min Act: -0.0001

Data Index: 1030435 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6853. Min Act: -0.0001

Data Index: 1056142 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7117. Min Act: -0.0001

Data Index: 837872 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7248. Min Act: -0.0001

Data Index: 1133659 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6978. Min Act: -0.0001

Data Index: 44455 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6711. Min Act: -0.0001

Data Index: 484304 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6928. Min Act: -0.0001

Data Index: 192325 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6652. Min Act: -0.0001

Data Index: 1190102 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6641. Min Act: -0.0001

Data Index: 658664 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6642. Min Act: -0.0001

Data Index: 601691 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6768. Min Act: -0.0001

Data Index: 618092 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6545. Min Act: -0.0001

Data Index: 567665 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6748. Min Act: -0.0001

Data Index: 78821 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6322. Min Act: -0.0001

Data Index: 330102 (C4 (Web Text))

Max Activating Token Index: 553