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

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

Neuron 1296 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1200. Min Act: -0.0001

Data Index: 432110 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1598413 (Python Code)

Max Activating Token Index: 426

Text #2

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1140. Min Act: -0.0001

Data Index: 1431607 (Python Code)

Max Activating Token Index: 506

Text #3

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1136. Min Act: -0.0001

Data Index: 510463 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1130. Min Act: -0.0001

Data Index: 765594 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1108. Min Act: -0.0001

Data Index: 521534 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1067. Min Act: -0.0001

Data Index: 1079429 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1095. Min Act: -0.0001

Data Index: 135453 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1061. Min Act: -0.0001

Data Index: 857443 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1053. Min Act: -0.0001

Data Index: 803147 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1376610 (Python Code)

Max Activating Token Index: 988

Text #11

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1049. Min Act: -0.0001

Data Index: 474842 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1020. Min Act: -0.0001

Data Index: 212824 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0996. Min Act: -0.0001

Data Index: 50418 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1021. Min Act: -0.0001

Data Index: 740392 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0989. Min Act: -0.0001

Data Index: 917051 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1154132 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1039. Min Act: -0.0001

Data Index: 1453638 (Python Code)

Max Activating Token Index: 768

Text #18

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1013. Min Act: -0.0001

Data Index: 1311225 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1059. Min Act: -0.0001

Data Index: 1593416 (Python Code)

Max Activating Token Index: 248