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

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

Neuron 3127 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: 1.2645. Min Range: -1.2645

Max Act: 1.2437. Min Act: -0.0000

Data Index: 112618 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.2645. Min Act: -0.0000

Data Index: 146220 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.1260. Min Act: -0.0000

Data Index: 943541 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.1125. Min Act: -0.0000

Data Index: 1218542 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.0995. Min Act: -0.0000

Data Index: 1062320 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.1600. Min Act: -0.0000

Data Index: 1354102 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.0554. Min Act: -0.0000

Data Index: 828288 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.1159. Min Act: -0.0000

Data Index: 209124 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.0311. Min Act: -0.0001

Data Index: 757424 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.0336. Min Act: -0.0000

Data Index: 1306639 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.0516. Min Act: -0.0000

Data Index: 69091 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.0494. Min Act: -0.0000

Data Index: 320070 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.0176. Min Act: -0.0000

Data Index: 238667 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.0114. Min Act: -0.0000

Data Index: 1337754 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.0390. Min Act: -0.0000

Data Index: 861694 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.0028. Min Act: -0.0000

Data Index: 172740 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.0310. Min Act: -0.0000

Data Index: 994826 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1347678 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.0119. Min Act: -0.0000

Data Index: 508385 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.0459. Min Act: -0.0000

Data Index: 662446 (C4 (Web Text))

Max Activating Token Index: 72