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

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

Neuron 1862 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0311. Min Range: -2.0311

Max Act: 2.0311. Min Act: -0.0000

Data Index: 1451036 (Python Code)

Max Activating Token Index: 811

Text #1

Max Range: 2.0311. Min Range: -2.0311

Max Act: 1.9917. Min Act: -0.0000

Data Index: 1523347 (Python Code)

Max Activating Token Index: 35

Text #2

Max Range: 2.0311. Min Range: -2.0311

Max Act: 2.0183. Min Act: -0.0000

Data Index: 1615600 (Python Code)

Max Activating Token Index: 872

Text #3

Max Range: 2.0311. Min Range: -2.0311

Max Act: 1.8951. Min Act: -0.0000

Data Index: 1488470 (Python Code)

Max Activating Token Index: 727

Text #4

Max Range: 2.0311. Min Range: -2.0311

Max Act: 1.7517. Min Act: -0.0000

Data Index: 1530193 (Python Code)

Max Activating Token Index: 35

Text #5

Max Range: 2.0311. Min Range: -2.0311

Max Act: 1.6665. Min Act: -0.0000

Data Index: 1624249 (Python Code)

Max Activating Token Index: 986

Text #6

Max Range: 2.0311. Min Range: -2.0311

Max Act: 1.6612. Min Act: -0.0000

Data Index: 1368544 (Python Code)

Max Activating Token Index: 39

Text #7

Max Range: 2.0311. Min Range: -2.0311

Max Act: 1.7128. Min Act: -0.0000

Data Index: 1588827 (Python Code)

Max Activating Token Index: 185

Text #8

Max Range: 2.0311. Min Range: -2.0311

Max Act: 1.5130. Min Act: -0.0000

Data Index: 1578637 (Python Code)

Max Activating Token Index: 580

Text #9

Max Range: 2.0311. Min Range: -2.0311

Max Act: 1.5705. Min Act: -0.0000

Data Index: 1591167 (Python Code)

Max Activating Token Index: 389

Text #10

Max Range: 2.0311. Min Range: -2.0311

Max Act: 1.5325. Min Act: -0.0000

Data Index: 1652379 (Python Code)

Max Activating Token Index: 316

Text #11

Max Range: 2.0311. Min Range: -2.0311

Max Act: 1.4716. Min Act: -0.0000

Data Index: 1633691 (Python Code)

Max Activating Token Index: 376

Text #12

Max Range: 2.0311. Min Range: -2.0311

Max Act: 1.4417. Min Act: -0.0000

Data Index: 1361278 (Python Code)

Max Activating Token Index: 824

Text #13

Max Range: 2.0311. Min Range: -2.0311

Max Act: 1.2937. Min Act: -0.0000

Data Index: 1628974 (Python Code)

Max Activating Token Index: 745

Text #14

Max Range: 2.0311. Min Range: -2.0311

Max Act: 1.3511. Min Act: -0.0000

Data Index: 1081460 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 2.0311. Min Range: -2.0311

Max Act: 1.2072. Min Act: -0.0000

Data Index: 1613351 (Python Code)

Max Activating Token Index: 171

Text #16

Max Range: 2.0311. Min Range: -2.0311

Max Act: 1.2870. Min Act: -0.0000

Data Index: 1231850 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 2.0311. Min Range: -2.0311

Max Act: 1.1971. Min Act: -0.0000

Data Index: 656129 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 2.0311. Min Range: -2.0311

Max Act: 1.2045. Min Act: -0.0000

Data Index: 1259936 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 2.0311. Min Range: -2.0311

Max Act: 1.1948. Min Act: -0.0000

Data Index: 780376 (C4 (Web Text))

Max Activating Token Index: 319