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

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

Neuron 2609 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.4508. Min Act: -0.0001

Data Index: 723918 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.2981. Min Act: -0.0001

Data Index: 1331066 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.3203. Min Act: -0.0000

Data Index: 238733 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.2065. Min Act: -0.0000

Data Index: 1257570 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.2087. Min Act: -0.0000

Data Index: 1205826 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.1950. Min Act: -0.0001

Data Index: 979423 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0669. Min Act: -0.0000

Data Index: 504714 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 1.4508. Min Range: -1.4508

Max Act: 0.9697. Min Act: -0.0001

Data Index: 125854 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0800. Min Act: -0.0001

Data Index: 566532 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0220. Min Act: -0.0001

Data Index: 927933 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0093. Min Act: -0.0000

Data Index: 172850 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0400. Min Act: -0.0001

Data Index: 1146252 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0069. Min Act: -0.0000

Data Index: 1018265 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0383. Min Act: -0.0000

Data Index: 1308835 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 1.4508. Min Range: -1.4508

Max Act: 0.9740. Min Act: -0.0001

Data Index: 992338 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 1.4508. Min Range: -1.4508

Max Act: 0.9725. Min Act: -0.0000

Data Index: 158677 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 1.4508. Min Range: -1.4508

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1151460 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0509. Min Act: -0.0001

Data Index: 964231 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 1.4508. Min Range: -1.4508

Max Act: 0.9345. Min Act: -0.0001

Data Index: 500492 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 1.4508. Min Range: -1.4508

Max Act: 0.9596. Min Act: -0.0001

Data Index: 1304575 (C4 (Web Text))

Max Activating Token Index: 493