Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 11 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1883. Min Act: -0.0000

Data Index: 504075 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1685. Min Act: -0.0000

Data Index: 467407 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1498. Min Act: -0.0000

Data Index: 272435 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1299. Min Act: -0.0000

Data Index: 678086 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1240. Min Act: -0.0000

Data Index: 1050171 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1198. Min Act: -0.0000

Data Index: 72916 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1240. Min Act: -0.0000

Data Index: 1319591 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1178. Min Act: -0.0000

Data Index: 1209346 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1196. Min Act: -0.0000

Data Index: 778571 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1138. Min Act: -0.0000

Data Index: 640225 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1205591 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1110. Min Act: -0.0000

Data Index: 909580 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1277327 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1181. Min Act: -0.0000

Data Index: 398676 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1118. Min Act: -0.0000

Data Index: 853007 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1139. Min Act: -0.0000

Data Index: 430824 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1055. Min Act: -0.0000

Data Index: 934067 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1050. Min Act: -0.0000

Data Index: 758910 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1122. Min Act: -0.0000

Data Index: 1220533 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1005. Min Act: -0.0000

Data Index: 21996 (C4 (Web Text))

Max Activating Token Index: 889