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

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

Neuron 5668 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.1748. Min Act: -0.0000

Data Index: 683345 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.1766. Min Act: -0.0000

Data Index: 217493 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.0670. Min Act: -0.0000

Data Index: 1249713 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.1061. Min Act: -0.0000

Data Index: 745504 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.0053. Min Act: -0.0000

Data Index: 454269 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.0708. Min Act: -0.0000

Data Index: 1219897 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.9969. Min Act: -0.0000

Data Index: 1110359 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.0526. Min Act: -0.0000

Data Index: 468326 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.1080. Min Act: -0.0000

Data Index: 546931 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.0325. Min Act: -0.0000

Data Index: 718019 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.0008. Min Act: -0.0000

Data Index: 953474 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.9984. Min Act: -0.0000

Data Index: 521297 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.0478. Min Act: -0.0000

Data Index: 1354100 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 1.1766. Min Range: -1.1766

Max Act: 1.0128. Min Act: -0.0000

Data Index: 9008 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.9755. Min Act: -0.0000

Data Index: 1339334 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.9408. Min Act: 0.0000

Data Index: 1263772 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.9695. Min Act: -0.0000

Data Index: 713344 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.9874. Min Act: -0.0000

Data Index: 1194521 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.9820. Min Act: -0.0000

Data Index: 279172 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 1.1766. Min Range: -1.1766

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1157991 (C4 (Web Text))

Max Activating Token Index: 887