Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1699 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.6947. Min Act: -0.0000

Data Index: 446282 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.6944. Min Act: -0.0000

Data Index: 48974 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.6334. Min Act: -0.0000

Data Index: 882619 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.6028. Min Act: -0.0000

Data Index: 970216 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.5785. Min Act: -0.0000

Data Index: 963724 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.5704. Min Act: -0.0000

Data Index: 991587 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.5496. Min Act: -0.0000

Data Index: 1345384 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.5158. Min Act: -0.0000

Data Index: 855103 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.5465. Min Act: -0.0000

Data Index: 690165 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1158540 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.5332. Min Act: -0.0000

Data Index: 37 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4372. Min Act: -0.0000

Data Index: 924975 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4971. Min Act: -0.0000

Data Index: 759055 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4774. Min Act: -0.0000

Data Index: 849314 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4663. Min Act: -0.0000

Data Index: 932491 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4631. Min Act: -0.0000

Data Index: 611234 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4721. Min Act: -0.0000

Data Index: 1155197 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4304. Min Act: -0.0000

Data Index: 301363 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4578. Min Act: -0.0000

Data Index: 66300 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4816. Min Act: -0.0000

Data Index: 270845 (C4 (Web Text))

Max Activating Token Index: 993