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

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

Neuron 4618 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: 0.1823. Min Range: -0.1823

Max Act: 0.1823. Min Act: -0.0000

Data Index: 181691 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1704. Min Act: -0.0000

Data Index: 264198 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1633. Min Act: -0.0000

Data Index: 891042 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1613. Min Act: -0.0000

Data Index: 407090 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1455. Min Act: -0.0000

Data Index: 661430 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1356. Min Act: -0.0000

Data Index: 1189536 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1281. Min Act: -0.0000

Data Index: 907595 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1330. Min Act: -0.0000

Data Index: 1214444 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1277. Min Act: -0.0000

Data Index: 583087 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1237. Min Act: -0.0000

Data Index: 545172 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1216. Min Act: -0.0000

Data Index: 515016 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1175. Min Act: -0.0000

Data Index: 246784 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1153. Min Act: -0.0000

Data Index: 948658 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1150443 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1079. Min Act: -0.0000

Data Index: 856115 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1049751 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1072. Min Act: -0.0000

Data Index: 926858 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1123. Min Act: -0.0000

Data Index: 54110 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1040. Min Act: -0.0000

Data Index: 368496 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1341604 (C4 (Web Text))

Max Activating Token Index: 644