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

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

Neuron 737 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: 0.1310. Min Range: -0.1310

Max Act: 0.1281. Min Act: -0.0001

Data Index: 856537 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1310. Min Act: -0.0001

Data Index: 1453048 (Python Code)

Max Activating Token Index: 311

Text #2

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1267. Min Act: -0.0001

Data Index: 1386355 (Python Code)

Max Activating Token Index: 215

Text #3

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1247. Min Act: -0.0002

Data Index: 190408 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1250. Min Act: -0.0002

Data Index: 1119992 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1236. Min Act: -0.0001

Data Index: 1160640 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1152. Min Act: -0.0001

Data Index: 1205836 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1231. Min Act: -0.0001

Data Index: 899729 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1147. Min Act: -0.0001

Data Index: 1073363 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1071. Min Act: -0.0001

Data Index: 280981 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1110. Min Act: -0.0002

Data Index: 661291 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1072. Min Act: -0.0001

Data Index: 333486 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1141. Min Act: -0.0001

Data Index: 732510 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1107. Min Act: -0.0001

Data Index: 937283 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1425796 (Python Code)

Max Activating Token Index: 56

Text #15

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1114. Min Act: -0.0002

Data Index: 1276368 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1054. Min Act: -0.0001

Data Index: 750137 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1090. Min Act: -0.0001

Data Index: 1397070 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1013. Min Act: -0.0001

Data Index: 1507739 (Python Code)

Max Activating Token Index: 271

Text #19

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1082. Min Act: -0.0002

Data Index: 501620 (C4 (Web Text))

Max Activating Token Index: 164