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

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

Neuron 5068 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2456. Min Range: -3.2456

Max Act: 3.2385. Min Act: -0.0000

Data Index: 814794 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 3.2456. Min Range: -3.2456

Max Act: 3.2456. Min Act: -0.0000

Data Index: 634391 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 3.2456. Min Range: -3.2456

Max Act: 2.3669. Min Act: -0.0000

Data Index: 21351 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 3.2456. Min Range: -3.2456

Max Act: 2.3377. Min Act: -0.0000

Data Index: 993019 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 3.2456. Min Range: -3.2456

Max Act: 2.3018. Min Act: -0.0000

Data Index: 1328825 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 3.2456. Min Range: -3.2456

Max Act: 2.1251. Min Act: -0.0000

Data Index: 1349616 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 3.2456. Min Range: -3.2456

Max Act: 2.0103. Min Act: -0.0000

Data Index: 126910 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 3.2456. Min Range: -3.2456

Max Act: 1.9628. Min Act: -0.0000

Data Index: 478478 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 3.2456. Min Range: -3.2456

Max Act: 1.9704. Min Act: -0.0000

Data Index: 4079 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 3.2456. Min Range: -3.2456

Max Act: 1.9676. Min Act: -0.0000

Data Index: 480978 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 3.2456. Min Range: -3.2456

Max Act: 1.9516. Min Act: -0.0000

Data Index: 386300 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 3.2456. Min Range: -3.2456

Max Act: 1.9290. Min Act: -0.0000

Data Index: 212093 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 3.2456. Min Range: -3.2456

Max Act: 1.9318. Min Act: -0.0000

Data Index: 146389 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 3.2456. Min Range: -3.2456

Max Act: 1.9173. Min Act: -0.0000

Data Index: 238721 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 3.2456. Min Range: -3.2456

Max Act: 1.8959. Min Act: -0.0000

Data Index: 715982 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 3.2456. Min Range: -3.2456

Max Act: 1.7125. Min Act: -0.0000

Data Index: 1468927 (Python Code)

Max Activating Token Index: 887

Text #16

Max Range: 3.2456. Min Range: -3.2456

Max Act: 1.8943. Min Act: -0.0000

Data Index: 338043 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 3.2456. Min Range: -3.2456

Max Act: 1.8735. Min Act: -0.0000

Data Index: 696805 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 3.2456. Min Range: -3.2456

Max Act: 1.7612. Min Act: -0.0000

Data Index: 716203 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 3.2456. Min Range: -3.2456

Max Act: 1.8651. Min Act: -0.0000

Data Index: 211735 (C4 (Web Text))

Max Activating Token Index: 426