Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3798 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2563. Min Act: -0.0001

Data Index: 764660 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2120. Min Act: -0.0001

Data Index: 402287 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1052566 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1984. Min Act: -0.0000

Data Index: 776458 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1817. Min Act: -0.0000

Data Index: 637637 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1393. Min Act: -0.0000

Data Index: 562606 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1435. Min Act: -0.0001

Data Index: 1433750 (Python Code)

Max Activating Token Index: 37

Text #7

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1325. Min Act: -0.0001

Data Index: 1422499 (Python Code)

Max Activating Token Index: 399

Text #8

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1089. Min Act: -0.0000

Data Index: 1228802 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1275. Min Act: -0.0001

Data Index: 49742 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1180. Min Act: -0.0001

Data Index: 1470311 (Python Code)

Max Activating Token Index: 1000

Text #11

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1110. Min Act: -0.0000

Data Index: 532040 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1128. Min Act: -0.0000

Data Index: 76355 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1192. Min Act: -0.0001

Data Index: 708730 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1144. Min Act: -0.0000

Data Index: 341886 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1098. Min Act: -0.0000

Data Index: 899134 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1115. Min Act: -0.0000

Data Index: 621362 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1033. Min Act: -0.0001

Data Index: 678507 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1102. Min Act: -0.0000

Data Index: 510189 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.1036. Min Act: -0.0000

Data Index: 558050 (C4 (Web Text))

Max Activating Token Index: 733