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

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

Neuron 2690 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2412. Min Act: -0.0001

Data Index: 63592 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2151. Min Act: -0.0001

Data Index: 828012 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2213. Min Act: -0.0000

Data Index: 583125 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1933. Min Act: -0.0000

Data Index: 599940 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1978. Min Act: -0.0000

Data Index: 517904 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1961. Min Act: -0.0000

Data Index: 285577 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1821. Min Act: -0.0000

Data Index: 47174 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1940. Min Act: -0.0001

Data Index: 174976 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1844. Min Act: -0.0000

Data Index: 112961 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1700. Min Act: -0.0001

Data Index: 552283 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1771. Min Act: -0.0000

Data Index: 427585 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1713. Min Act: -0.0001

Data Index: 654553 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1731. Min Act: -0.0000

Data Index: 1081876 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1718. Min Act: -0.0001

Data Index: 827896 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1718. Min Act: -0.0001

Data Index: 1449875 (Python Code)

Max Activating Token Index: 719

Text #15

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1632. Min Act: -0.0000

Data Index: 350310 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1625. Min Act: -0.0000

Data Index: 762031 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1735. Min Act: -0.0001

Data Index: 1049958 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1683. Min Act: -0.0000

Data Index: 659026 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1584. Min Act: -0.0000

Data Index: 370792 (C4 (Web Text))

Max Activating Token Index: 820