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

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

Neuron 1538 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: 4.0352. Min Range: -4.0352

Max Act: 4.0352. Min Act: -0.0000

Data Index: 918491 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 4.0352. Min Range: -4.0352

Max Act: 3.8718. Min Act: -0.0000

Data Index: 201084 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 4.0352. Min Range: -4.0352

Max Act: 3.6132. Min Act: -0.0000

Data Index: 513006 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 4.0352. Min Range: -4.0352

Max Act: 3.2798. Min Act: -0.0000

Data Index: 419288 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 4.0352. Min Range: -4.0352

Max Act: 3.0391. Min Act: -0.0000

Data Index: 86884 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 4.0352. Min Range: -4.0352

Max Act: 3.0224. Min Act: -0.0000

Data Index: 108410 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 4.0352. Min Range: -4.0352

Max Act: 3.3215. Min Act: -0.0000

Data Index: 1025137 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 4.0352. Min Range: -4.0352

Max Act: 2.9982. Min Act: -0.0000

Data Index: 6073 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 4.0352. Min Range: -4.0352

Max Act: 3.1321. Min Act: -0.0000

Data Index: 729924 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 4.0352. Min Range: -4.0352

Max Act: 2.9669. Min Act: -0.0000

Data Index: 622133 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 4.0352. Min Range: -4.0352

Max Act: 2.9861. Min Act: -0.0000

Data Index: 493200 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 4.0352. Min Range: -4.0352

Max Act: 3.0512. Min Act: -0.0000

Data Index: 390533 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 4.0352. Min Range: -4.0352

Max Act: 2.8990. Min Act: -0.0000

Data Index: 291852 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 4.0352. Min Range: -4.0352

Max Act: 2.8883. Min Act: -0.0000

Data Index: 1313724 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 4.0352. Min Range: -4.0352

Max Act: 2.7044. Min Act: -0.0000

Data Index: 1257502 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 4.0352. Min Range: -4.0352

Max Act: 2.8549. Min Act: -0.0000

Data Index: 1139195 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 4.0352. Min Range: -4.0352

Max Act: 3.0172. Min Act: -0.0000

Data Index: 1190821 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 4.0352. Min Range: -4.0352

Max Act: 2.8255. Min Act: -0.0000

Data Index: 47866 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 4.0352. Min Range: -4.0352

Max Act: 2.8841. Min Act: -0.0000

Data Index: 1185350 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 4.0352. Min Range: -4.0352

Max Act: 2.5767. Min Act: -0.0000

Data Index: 955103 (C4 (Web Text))

Max Activating Token Index: 195