Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4425 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2224. Min Act: -0.0001

Data Index: 1343299 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2149. Min Act: -0.0001

Data Index: 182647 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2309. Min Act: -0.0001

Data Index: 159536 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2304. Min Act: -0.0001

Data Index: 1145323 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2406. Min Act: -0.0001

Data Index: 796365 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2168. Min Act: -0.0001

Data Index: 897105 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2298. Min Act: -0.0001

Data Index: 496619 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2211. Min Act: -0.0001

Data Index: 266244 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2064. Min Act: -0.0001

Data Index: 30097 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2074. Min Act: -0.0001

Data Index: 1339988 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2124. Min Act: -0.0001

Data Index: 1117146 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2120. Min Act: -0.0001

Data Index: 1351892 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2244. Min Act: -0.0001

Data Index: 490680 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2179. Min Act: -0.0001

Data Index: 778560 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2148. Min Act: -0.0001

Data Index: 652848 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2175. Min Act: -0.0001

Data Index: 127655 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2135. Min Act: -0.0001

Data Index: 15413 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2097. Min Act: -0.0001

Data Index: 180084 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2142. Min Act: -0.0001

Data Index: 874371 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1988. Min Act: -0.0001

Data Index: 243079 (C4 (Web Text))

Max Activating Token Index: 282