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

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

Neuron 711 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2675. Min Act: -0.0001

Data Index: 68652 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2494. Min Act: -0.0001

Data Index: 789568 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2494. Min Act: -0.0001

Data Index: 415885 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2165. Min Act: -0.0001

Data Index: 50878 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2451. Min Act: -0.0001

Data Index: 225879 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2381. Min Act: -0.0001

Data Index: 1154521 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2267. Min Act: -0.0001

Data Index: 804498 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2218. Min Act: -0.0001

Data Index: 992115 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2182. Min Act: -0.0001

Data Index: 793627 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2419. Min Act: -0.0001

Data Index: 556580 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2191. Min Act: -0.0001

Data Index: 651634 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2182. Min Act: -0.0001

Data Index: 362618 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2073. Min Act: -0.0001

Data Index: 1019876 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2274. Min Act: -0.0001

Data Index: 1052735 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2262. Min Act: -0.0001

Data Index: 464028 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2153. Min Act: -0.0001

Data Index: 917227 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2125. Min Act: -0.0001

Data Index: 1179522 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2185. Min Act: -0.0001

Data Index: 230498 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2120. Min Act: -0.0001

Data Index: 427814 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.2675. Min Range: -0.2675

Max Act: 0.2047. Min Act: -0.0001

Data Index: 1123946 (C4 (Web Text))

Max Activating Token Index: 212