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

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

Neuron 16 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1899. Min Act: -0.0001

Data Index: 1343597 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1498. Min Act: -0.0001

Data Index: 1495281 (Python Code)

Max Activating Token Index: 1020

Text #2

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1390. Min Act: -0.0000

Data Index: 100396 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1388. Min Act: -0.0001

Data Index: 1005701 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1254. Min Act: -0.0001

Data Index: 1426637 (Python Code)

Max Activating Token Index: 780

Text #5

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1293. Min Act: -0.0001

Data Index: 1198528 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1278. Min Act: -0.0001

Data Index: 774352 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1190. Min Act: -0.0001

Data Index: 787491 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1184. Min Act: -0.0001

Data Index: 572974 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1223. Min Act: -0.0001

Data Index: 1169714 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1198. Min Act: -0.0001

Data Index: 1014370 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1060. Min Act: -0.0001

Data Index: 652416 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1202. Min Act: -0.0001

Data Index: 1220378 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1157. Min Act: -0.0000

Data Index: 778973 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1132. Min Act: -0.0001

Data Index: 1324292 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1134. Min Act: -0.0001

Data Index: 498757 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1112. Min Act: -0.0001

Data Index: 473329 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1059. Min Act: -0.0001

Data Index: 907999 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1071. Min Act: -0.0001

Data Index: 1407538 (Python Code)

Max Activating Token Index: 340

Text #19

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1070. Min Act: -0.0001

Data Index: 1466573 (Python Code)

Max Activating Token Index: 421