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

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

Neuron 3690 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1406. Min Act: -0.0001

Data Index: 1638767 (Python Code)

Max Activating Token Index: 106

Text #1

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1336100 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1179. Min Act: -0.0002

Data Index: 739770 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1225. Min Act: -0.0002

Data Index: 1163994 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1163. Min Act: -0.0002

Data Index: 1336504 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1124. Min Act: -0.0001

Data Index: 389005 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1210. Min Act: -0.0002

Data Index: 433889 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1129. Min Act: -0.0001

Data Index: 45151 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1472749 (Python Code)

Max Activating Token Index: 353

Text #9

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1081. Min Act: -0.0001

Data Index: 522829 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1092. Min Act: -0.0001

Data Index: 1626081 (Python Code)

Max Activating Token Index: 783

Text #11

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1040. Min Act: -0.0002

Data Index: 291961 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1101. Min Act: -0.0002

Data Index: 1309259 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1108. Min Act: -0.0001

Data Index: 368286 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1063. Min Act: -0.0002

Data Index: 1461681 (Python Code)

Max Activating Token Index: 234

Text #15

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1075. Min Act: -0.0002

Data Index: 1252727 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0971. Min Act: -0.0002

Data Index: 48264 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1092. Min Act: -0.0002

Data Index: 457143 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0988. Min Act: -0.0002

Data Index: 973728 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1025. Min Act: -0.0002

Data Index: 17969 (C4 (Web Text))

Max Activating Token Index: 294