Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2448 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2450. Min Act: -0.0001

Data Index: 42278 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2365. Min Act: -0.0001

Data Index: 604913 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2287. Min Act: -0.0001

Data Index: 944211 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2171. Min Act: -0.0001

Data Index: 593937 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1906. Min Act: -0.0001

Data Index: 831463 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1894. Min Act: -0.0001

Data Index: 176702 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1850. Min Act: -0.0001

Data Index: 837843 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1916. Min Act: -0.0001

Data Index: 1321214 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1860. Min Act: -0.0001

Data Index: 922839 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1901. Min Act: -0.0001

Data Index: 400925 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1888. Min Act: -0.0001

Data Index: 458555 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1758. Min Act: -0.0001

Data Index: 401805 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1795. Min Act: -0.0001

Data Index: 627679 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1680. Min Act: -0.0001

Data Index: 1045714 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1790. Min Act: -0.0001

Data Index: 1129320 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1801. Min Act: -0.0001

Data Index: 396298 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1788. Min Act: -0.0001

Data Index: 702070 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1611. Min Act: -0.0001

Data Index: 607087 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1709. Min Act: -0.0001

Data Index: 1088553 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1654. Min Act: -0.0001

Data Index: 1257944 (C4 (Web Text))

Max Activating Token Index: 719