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

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

Neuron 5204 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.8119. Min Act: -0.0000

Data Index: 1350198 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.7737. Min Act: -0.0001

Data Index: 258292 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.5155. Min Act: -0.0000

Data Index: 172516 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.5433. Min Act: -0.0001

Data Index: 17558 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.5642. Min Act: -0.0000

Data Index: 768749 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.5237. Min Act: -0.0000

Data Index: 991840 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.5200. Min Act: -0.0000

Data Index: 346877 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.4634. Min Act: -0.0000

Data Index: 123230 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.4765. Min Act: -0.0000

Data Index: 1305191 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.5249. Min Act: -0.0000

Data Index: 977912 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.5247. Min Act: -0.0001

Data Index: 326647 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.3972. Min Act: -0.0000

Data Index: 1174982 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.5216. Min Act: -0.0000

Data Index: 1136962 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.3624. Min Act: -0.0001

Data Index: 264058 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.3675. Min Act: -0.0000

Data Index: 442364 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.3470. Min Act: -0.0000

Data Index: 807680 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.3276. Min Act: -0.0001

Data Index: 1125727 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.2365. Min Act: -0.0001

Data Index: 794652 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.3191. Min Act: -0.0000

Data Index: 337015 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 1.8119. Min Range: -1.8119

Max Act: 1.3603. Min Act: -0.0000

Data Index: 1265540 (C4 (Web Text))

Max Activating Token Index: 50