Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4733 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7572. Min Range: -2.7572

Max Act: 2.7572. Min Act: -0.0000

Data Index: 1071420 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 2.7572. Min Range: -2.7572

Max Act: 2.6678. Min Act: -0.0000

Data Index: 994569 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 2.7572. Min Range: -2.7572

Max Act: 2.4937. Min Act: -0.0000

Data Index: 222984 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 2.7572. Min Range: -2.7572

Max Act: 2.4006. Min Act: -0.0000

Data Index: 383575 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 2.7572. Min Range: -2.7572

Max Act: 2.3652. Min Act: -0.0000

Data Index: 5080 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 2.7572. Min Range: -2.7572

Max Act: 2.4806. Min Act: -0.0000

Data Index: 177296 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 2.7572. Min Range: -2.7572

Max Act: 2.5130. Min Act: -0.0000

Data Index: 875846 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 2.7572. Min Range: -2.7572

Max Act: 2.1917. Min Act: -0.0000

Data Index: 144724 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 2.7572. Min Range: -2.7572

Max Act: 2.1656. Min Act: -0.0000

Data Index: 391990 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 2.7572. Min Range: -2.7572

Max Act: 2.2619. Min Act: -0.0000

Data Index: 946058 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 2.7572. Min Range: -2.7572

Max Act: 2.3713. Min Act: -0.0000

Data Index: 167580 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 2.7572. Min Range: -2.7572

Max Act: 2.1727. Min Act: -0.0000

Data Index: 1165409 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 2.7572. Min Range: -2.7572

Max Act: 2.0199. Min Act: -0.0000

Data Index: 1099622 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 2.7572. Min Range: -2.7572

Max Act: 2.1193. Min Act: -0.0000

Data Index: 48741 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 2.7572. Min Range: -2.7572

Max Act: 2.1122. Min Act: -0.0000

Data Index: 14795 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 2.7572. Min Range: -2.7572

Max Act: 1.9945. Min Act: -0.0000

Data Index: 342486 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 2.7572. Min Range: -2.7572

Max Act: 2.0097. Min Act: -0.0000

Data Index: 1013109 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 2.7572. Min Range: -2.7572

Max Act: 2.0071. Min Act: -0.0000

Data Index: 1261146 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 2.7572. Min Range: -2.7572

Max Act: 2.0066. Min Act: -0.0000

Data Index: 802484 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 2.7572. Min Range: -2.7572

Max Act: 1.9494. Min Act: -0.0000

Data Index: 978610 (C4 (Web Text))

Max Activating Token Index: 317