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

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

Neuron 530 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1704. Min Act: -0.0001

Data Index: 1310497 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1135. Min Act: -0.0001

Data Index: 1300531 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1172. Min Act: -0.0001

Data Index: 907872 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1053. Min Act: -0.0001

Data Index: 840572 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1577091 (Python Code)

Max Activating Token Index: 350

Text #5

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1232. Min Act: -0.0001

Data Index: 174556 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1075. Min Act: -0.0001

Data Index: 907913 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1213. Min Act: -0.0001

Data Index: 149939 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1169. Min Act: -0.0001

Data Index: 792517 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1232. Min Act: -0.0001

Data Index: 327034 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1178. Min Act: -0.0001

Data Index: 936875 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1167. Min Act: -0.0001

Data Index: 109015 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1076. Min Act: -0.0001

Data Index: 1524948 (Python Code)

Max Activating Token Index: 316

Text #13

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1198. Min Act: -0.0001

Data Index: 1190573 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1282859 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1493145 (Python Code)

Max Activating Token Index: 317

Text #16

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1103. Min Act: -0.0001

Data Index: 839782 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1147. Min Act: -0.0001

Data Index: 698287 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1144. Min Act: -0.0001

Data Index: 967901 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1047. Min Act: -0.0002

Data Index: 492205 (C4 (Web Text))

Max Activating Token Index: 149