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

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

Neuron 1032 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: 0.5572. Min Range: -0.5572

Max Act: 0.5572. Min Act: -0.0000

Data Index: 1348815 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.4282. Min Act: -0.0000

Data Index: 382012 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.4397. Min Act: -0.0001

Data Index: 131740 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.3832. Min Act: -0.0000

Data Index: 295416 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.3945. Min Act: -0.0000

Data Index: 528210 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.3836. Min Act: -0.0001

Data Index: 1534996 (Python Code)

Max Activating Token Index: 1006

Text #6

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.3773. Min Act: -0.0001

Data Index: 1596536 (Python Code)

Max Activating Token Index: 952

Text #7

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.3541. Min Act: -0.0000

Data Index: 286049 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.3624. Min Act: -0.0001

Data Index: 1400655 (Python Code)

Max Activating Token Index: 681

Text #9

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.3339. Min Act: -0.0000

Data Index: 918051 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.3564. Min Act: -0.0001

Data Index: 1504645 (Python Code)

Max Activating Token Index: 427

Text #11

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.3288. Min Act: -0.0001

Data Index: 1452306 (Python Code)

Max Activating Token Index: 1018

Text #12

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.2840. Min Act: -0.0000

Data Index: 484240 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.3193. Min Act: -0.0001

Data Index: 1496059 (Python Code)

Max Activating Token Index: 988

Text #14

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.3271. Min Act: -0.0000

Data Index: 961721 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.3178. Min Act: -0.0001

Data Index: 1445996 (Python Code)

Max Activating Token Index: 269

Text #16

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.3072. Min Act: -0.0001

Data Index: 1594239 (Python Code)

Max Activating Token Index: 140

Text #17

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.3268. Min Act: -0.0001

Data Index: 1613586 (Python Code)

Max Activating Token Index: 886

Text #18

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.3119. Min Act: -0.0001

Data Index: 1557430 (Python Code)

Max Activating Token Index: 983

Text #19

Max Range: 0.5572. Min Range: -0.5572

Max Act: 0.3097. Min Act: -0.0001

Data Index: 1423371 (Python Code)

Max Activating Token Index: 846