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

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

Neuron 3560 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: 0.3150. Min Range: -0.3150

Max Act: 0.3150. Min Act: -0.0001

Data Index: 1178663 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2429. Min Act: -0.0001

Data Index: 196179 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1988. Min Act: -0.0001

Data Index: 266181 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2020. Min Act: -0.0001

Data Index: 42437 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1870. Min Act: -0.0001

Data Index: 787858 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1856. Min Act: -0.0001

Data Index: 1280029 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1830. Min Act: -0.0001

Data Index: 1253746 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1736. Min Act: -0.0000

Data Index: 602333 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1770. Min Act: -0.0001

Data Index: 95260 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1625. Min Act: -0.0001

Data Index: 1162218 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1950. Min Act: -0.0001

Data Index: 1205791 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1759. Min Act: -0.0001

Data Index: 316700 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1581. Min Act: -0.0001

Data Index: 693361 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1639. Min Act: -0.0001

Data Index: 951708 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1733. Min Act: -0.0001

Data Index: 171515 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1652. Min Act: -0.0001

Data Index: 1310117 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1560. Min Act: -0.0001

Data Index: 820948 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1529. Min Act: -0.0001

Data Index: 669782 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1688. Min Act: -0.0001

Data Index: 857356 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.1493. Min Act: -0.0001

Data Index: 750929 (C4 (Web Text))

Max Activating Token Index: 296