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

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

Neuron 195 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.8383. Min Act: -0.0000

Data Index: 632099 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.8283. Min Act: -0.0000

Data Index: 1190287 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.7597. Min Act: -0.0000

Data Index: 766523 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.3147. Min Act: -0.0000

Data Index: 500969 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.3394. Min Act: -0.0000

Data Index: 360252 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.4186. Min Act: -0.0000

Data Index: 1161003 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.4113. Min Act: -0.0000

Data Index: 539267 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.3238. Min Act: -0.0000

Data Index: 842572 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.3466. Min Act: -0.0000

Data Index: 605503 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.2842. Min Act: -0.0000

Data Index: 258633 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.2039. Min Act: -0.0000

Data Index: 46354 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.2964. Min Act: -0.0001

Data Index: 544175 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.1864. Min Act: -0.0000

Data Index: 1257389 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.1840. Min Act: -0.0000

Data Index: 854289 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.1768. Min Act: -0.0000

Data Index: 500587 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.2109. Min Act: -0.0000

Data Index: 815639 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.0859. Min Act: -0.0000

Data Index: 1294996 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.2191. Min Act: -0.0000

Data Index: 874189 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.1953. Min Act: -0.0000

Data Index: 81398 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.0939. Min Act: -0.0000

Data Index: 985784 (C4 (Web Text))

Max Activating Token Index: 541