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

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

Neuron 3210 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6602. Min Range: -2.6602

Max Act: 2.6602. Min Act: -0.0000

Data Index: 1625757 (Python Code)

Max Activating Token Index: 233

Text #1

Max Range: 2.6602. Min Range: -2.6602

Max Act: 2.2236. Min Act: -0.0000

Data Index: 113184 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 2.6602. Min Range: -2.6602

Max Act: 2.0385. Min Act: -0.0001

Data Index: 1445674 (Python Code)

Max Activating Token Index: 827

Text #3

Max Range: 2.6602. Min Range: -2.6602

Max Act: 2.1072. Min Act: -0.0000

Data Index: 1647632 (Python Code)

Max Activating Token Index: 134

Text #4

Max Range: 2.6602. Min Range: -2.6602

Max Act: 2.0869. Min Act: -0.0000

Data Index: 1653738 (Python Code)

Max Activating Token Index: 303

Text #5

Max Range: 2.6602. Min Range: -2.6602

Max Act: 2.0676. Min Act: -0.0000

Data Index: 1530834 (Python Code)

Max Activating Token Index: 36

Text #6

Max Range: 2.6602. Min Range: -2.6602

Max Act: 1.9597. Min Act: -0.0000

Data Index: 1509458 (Python Code)

Max Activating Token Index: 227

Text #7

Max Range: 2.6602. Min Range: -2.6602

Max Act: 2.1682. Min Act: -0.0000

Data Index: 1388871 (Python Code)

Max Activating Token Index: 107

Text #8

Max Range: 2.6602. Min Range: -2.6602

Max Act: 1.9566. Min Act: -0.0000

Data Index: 1368687 (Python Code)

Max Activating Token Index: 94

Text #9

Max Range: 2.6602. Min Range: -2.6602

Max Act: 2.0559. Min Act: -0.0000

Data Index: 1416505 (Python Code)

Max Activating Token Index: 161

Text #10

Max Range: 2.6602. Min Range: -2.6602

Max Act: 1.8344. Min Act: -0.0000

Data Index: 1397930 (Python Code)

Max Activating Token Index: 152

Text #11

Max Range: 2.6602. Min Range: -2.6602

Max Act: 2.0327. Min Act: -0.0000

Data Index: 1516472 (Python Code)

Max Activating Token Index: 143

Text #12

Max Range: 2.6602. Min Range: -2.6602

Max Act: 1.9799. Min Act: -0.0000

Data Index: 1396961 (Python Code)

Max Activating Token Index: 340

Text #13

Max Range: 2.6602. Min Range: -2.6602

Max Act: 1.9950. Min Act: -0.0000

Data Index: 1301745 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 2.6602. Min Range: -2.6602

Max Act: 1.9104. Min Act: -0.0000

Data Index: 1443380 (Python Code)

Max Activating Token Index: 146

Text #15

Max Range: 2.6602. Min Range: -2.6602

Max Act: 1.9222. Min Act: -0.0000

Data Index: 1652891 (Python Code)

Max Activating Token Index: 106

Text #16

Max Range: 2.6602. Min Range: -2.6602

Max Act: 1.9463. Min Act: -0.0000

Data Index: 1392387 (Python Code)

Max Activating Token Index: 442

Text #17

Max Range: 2.6602. Min Range: -2.6602

Max Act: 1.9929. Min Act: -0.0001

Data Index: 1541139 (Python Code)

Max Activating Token Index: 832

Text #18

Max Range: 2.6602. Min Range: -2.6602

Max Act: 2.0384. Min Act: -0.0000

Data Index: 1497916 (Python Code)

Max Activating Token Index: 901

Text #19

Max Range: 2.6602. Min Range: -2.6602

Max Act: 2.0085. Min Act: -0.0000

Data Index: 1479665 (Python Code)

Max Activating Token Index: 95