Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4747 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2072. Min Range: -1.2072

Max Act: 1.2072. Min Act: -0.0000

Data Index: 1496081 (Python Code)

Max Activating Token Index: 577

Text #1

Max Range: 1.2072. Min Range: -1.2072

Max Act: 1.1108. Min Act: -0.0000

Data Index: 1453525 (Python Code)

Max Activating Token Index: 386

Text #2

Max Range: 1.2072. Min Range: -1.2072

Max Act: 1.0460. Min Act: -0.0001

Data Index: 1621790 (Python Code)

Max Activating Token Index: 434

Text #3

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.9629. Min Act: -0.0000

Data Index: 1581058 (Python Code)

Max Activating Token Index: 895

Text #4

Max Range: 1.2072. Min Range: -1.2072

Max Act: 1.0439. Min Act: -0.0001

Data Index: 423123 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 1.2072. Min Range: -1.2072

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1367955 (Python Code)

Max Activating Token Index: 277

Text #6

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.9946. Min Act: -0.0001

Data Index: 1564644 (Python Code)

Max Activating Token Index: 878

Text #7

Max Range: 1.2072. Min Range: -1.2072

Max Act: 1.0255. Min Act: -0.0001

Data Index: 1498210 (Python Code)

Max Activating Token Index: 235

Text #8

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.9800. Min Act: -0.0000

Data Index: 1624016 (Python Code)

Max Activating Token Index: 679

Text #9

Max Range: 1.2072. Min Range: -1.2072

Max Act: 1.0043. Min Act: -0.0001

Data Index: 1536956 (Python Code)

Max Activating Token Index: 716

Text #10

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.9352. Min Act: -0.0001

Data Index: 573565 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.9310. Min Act: -0.0001

Data Index: 655003 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.9484. Min Act: -0.0001

Data Index: 1488902 (Python Code)

Max Activating Token Index: 844

Text #13

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.9188. Min Act: -0.0000

Data Index: 433855 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 1.2072. Min Range: -1.2072

Max Act: 1.0168. Min Act: -0.0001

Data Index: 1463263 (Python Code)

Max Activating Token Index: 691

Text #15

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.9022. Min Act: -0.0000

Data Index: 1456874 (Python Code)

Max Activating Token Index: 67

Text #16

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.9614. Min Act: -0.0001

Data Index: 1312996 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.9512. Min Act: -0.0000

Data Index: 1391599 (Python Code)

Max Activating Token Index: 705

Text #18

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.9003. Min Act: -0.0000

Data Index: 227027 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.9095. Min Act: -0.0001

Data Index: 1323513 (C4 (Web Text))

Max Activating Token Index: 730