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

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

Neuron 864 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: 2.8749. Min Range: -2.8749

Max Act: 2.8749. Min Act: -0.0000

Data Index: 259170 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.6107. Min Act: -0.0000

Data Index: 1586384 (Python Code)

Max Activating Token Index: 676

Text #2

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.6684. Min Act: -0.0000

Data Index: 1579323 (Python Code)

Max Activating Token Index: 991

Text #3

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.1732. Min Act: -0.0000

Data Index: 1464201 (Python Code)

Max Activating Token Index: 215

Text #4

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.1061. Min Act: -0.0000

Data Index: 675309 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.9587. Min Act: -0.0000

Data Index: 513188 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.0611. Min Act: -0.0000

Data Index: 349830 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.9304. Min Act: -0.0000

Data Index: 1602601 (Python Code)

Max Activating Token Index: 682

Text #8

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.0222. Min Act: -0.0000

Data Index: 1441409 (Python Code)

Max Activating Token Index: 838

Text #9

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.8662. Min Act: -0.0000

Data Index: 52236 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.8225. Min Act: -0.0000

Data Index: 804522 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.5905. Min Act: -0.0000

Data Index: 1511753 (Python Code)

Max Activating Token Index: 381

Text #12

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.8874. Min Act: -0.0000

Data Index: 1581879 (Python Code)

Max Activating Token Index: 668

Text #13

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.6920. Min Act: -0.0000

Data Index: 1594146 (Python Code)

Max Activating Token Index: 275

Text #14

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.6891. Min Act: -0.0000

Data Index: 1453868 (Python Code)

Max Activating Token Index: 873

Text #15

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.6130. Min Act: -0.0000

Data Index: 1534701 (Python Code)

Max Activating Token Index: 442

Text #16

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.6678. Min Act: -0.0000

Data Index: 297005 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.5936. Min Act: -0.0000

Data Index: 873236 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.7477. Min Act: -0.0000

Data Index: 1432095 (Python Code)

Max Activating Token Index: 770

Text #19

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.5689. Min Act: -0.0000

Data Index: 1449496 (Python Code)

Max Activating Token Index: 608