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

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

Neuron 3800 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: 0.4607. Min Range: -0.4607

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1560284 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1379943 (Python Code)

Max Activating Token Index: 292

Text #2

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.4601. Min Act: -0.0000

Data Index: 1373810 (Python Code)

Max Activating Token Index: 617

Text #3

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1555298 (Python Code)

Max Activating Token Index: 511

Text #4

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1433360 (Python Code)

Max Activating Token Index: 992

Text #5

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1379701 (Python Code)

Max Activating Token Index: 622

Text #6

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1450821 (Python Code)

Max Activating Token Index: 696

Text #7

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1568830 (Python Code)

Max Activating Token Index: 345

Text #8

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1468957 (Python Code)

Max Activating Token Index: 314

Text #9

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1542628 (Python Code)

Max Activating Token Index: 936

Text #10

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1366484 (Python Code)

Max Activating Token Index: 653

Text #11

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.3975. Min Act: -0.0000

Data Index: 1598015 (Python Code)

Max Activating Token Index: 62

Text #12

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1564386 (Python Code)

Max Activating Token Index: 545

Text #13

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.3919. Min Act: -0.0000

Data Index: 1393806 (Python Code)

Max Activating Token Index: 857

Text #14

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1594617 (Python Code)

Max Activating Token Index: 579

Text #15

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.3873. Min Act: -0.0000

Data Index: 1622691 (Python Code)

Max Activating Token Index: 639

Text #16

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1652826 (Python Code)

Max Activating Token Index: 221

Text #17

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1620510 (Python Code)

Max Activating Token Index: 166

Text #18

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.3664. Min Act: -0.0000

Data Index: 1365164 (Python Code)

Max Activating Token Index: 363

Text #19

Max Range: 0.4607. Min Range: -0.4607

Max Act: 0.3770. Min Act: -0.0000

Data Index: 1594243 (Python Code)

Max Activating Token Index: 113