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

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

Neuron 1905 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1805. Min Act: -0.0000

Data Index: 450756 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1619. Min Act: -0.0000

Data Index: 1109567 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1522. Min Act: -0.0000

Data Index: 855978 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1310. Min Act: -0.0000

Data Index: 1230217 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1186. Min Act: -0.0000

Data Index: 1628628 (Python Code)

Max Activating Token Index: 35

Text #5

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1539512 (Python Code)

Max Activating Token Index: 228

Text #6

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1174. Min Act: -0.0000

Data Index: 830352 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1164. Min Act: -0.0000

Data Index: 1006053 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1066. Min Act: -0.0000

Data Index: 626572 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1105. Min Act: -0.0000

Data Index: 838705 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.0923. Min Act: -0.0000

Data Index: 630600 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.0925. Min Act: -0.0000

Data Index: 1541023 (Python Code)

Max Activating Token Index: 675

Text #12

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.0953. Min Act: -0.0000

Data Index: 110793 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1002534 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.0909. Min Act: -0.0000

Data Index: 821247 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.0912. Min Act: -0.0000

Data Index: 482217 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.0891. Min Act: -0.0000

Data Index: 668433 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1264795 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.0746. Min Act: -0.0000

Data Index: 821062 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.0824. Min Act: -0.0000

Data Index: 398060 (C4 (Web Text))

Max Activating Token Index: 344