Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2025 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.3059. Min Act: -0.0001

Data Index: 1298930 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1284156 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2404. Min Act: -0.0000

Data Index: 724419 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2543. Min Act: -0.0000

Data Index: 9723 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2123. Min Act: -0.0000

Data Index: 946 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2304. Min Act: -0.0001

Data Index: 606245 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2215. Min Act: -0.0000

Data Index: 497861 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1916. Min Act: -0.0001

Data Index: 1304330 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2068. Min Act: -0.0001

Data Index: 1140563 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1816. Min Act: -0.0001

Data Index: 485125 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1187150 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1652. Min Act: -0.0000

Data Index: 230538 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1700. Min Act: -0.0000

Data Index: 999264 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1695. Min Act: -0.0001

Data Index: 1168259 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1737. Min Act: -0.0001

Data Index: 862024 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1653. Min Act: -0.0000

Data Index: 112657 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1652. Min Act: -0.0000

Data Index: 162252 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1823. Min Act: -0.0001

Data Index: 607189 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1678. Min Act: -0.0000

Data Index: 323686 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.1699. Min Act: -0.0000

Data Index: 715419 (C4 (Web Text))

Max Activating Token Index: 87