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

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

Neuron 2039 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4549. Min Act: -0.0000

Data Index: 302593 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3675. Min Act: -0.0000

Data Index: 962590 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3506. Min Act: -0.0000

Data Index: 894328 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3433. Min Act: -0.0000

Data Index: 96851 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3455. Min Act: -0.0000

Data Index: 52449 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3204. Min Act: -0.0000

Data Index: 250760 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3459. Min Act: -0.0000

Data Index: 541619 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3323. Min Act: -0.0000

Data Index: 1305519 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3243. Min Act: -0.0000

Data Index: 840474 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3272. Min Act: -0.0000

Data Index: 969381 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3249. Min Act: -0.0000

Data Index: 673526 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3249. Min Act: -0.0000

Data Index: 504423 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3256. Min Act: -0.0000

Data Index: 1245116 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3151. Min Act: -0.0000

Data Index: 498793 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3082. Min Act: -0.0000

Data Index: 1358688 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.2962. Min Act: -0.0000

Data Index: 480472 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3054. Min Act: -0.0000

Data Index: 1122689 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.2940. Min Act: -0.0000

Data Index: 1327568 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.2907. Min Act: -0.0000

Data Index: 491964 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3095. Min Act: -0.0000

Data Index: 404092 (C4 (Web Text))

Max Activating Token Index: 976