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

Dataset: The Pile

Neuron 3970 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2694. Min Act: 0.0000

Data Index: 67309 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2578. Min Act: 0.0000

Data Index: 1126147 (The Pile)

Max Activating Token Index: 78

Text #2

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2367. Min Act: 0.0000

Data Index: 1359572 (The Pile)

Max Activating Token Index: 573

Text #3

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2319. Min Act: 0.0000

Data Index: 935599 (The Pile)

Max Activating Token Index: 209

Text #4

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2240. Min Act: 0.0000

Data Index: 61083 (The Pile)

Max Activating Token Index: 161

Text #5

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2210. Min Act: 0.0000

Data Index: 699161 (The Pile)

Max Activating Token Index: 88

Text #6

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2205. Min Act: 0.0000

Data Index: 1813559 (The Pile)

Max Activating Token Index: 393

Text #7

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2203. Min Act: 0.0000

Data Index: 145362 (The Pile)

Max Activating Token Index: 2

Text #8

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2186. Min Act: 0.0000

Data Index: 81215 (The Pile)

Max Activating Token Index: 540

Text #9

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2178. Min Act: 0.0000

Data Index: 416182 (The Pile)

Max Activating Token Index: 232

Text #10

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2168. Min Act: 0.0000

Data Index: 231155 (The Pile)

Max Activating Token Index: 175

Text #11

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2171. Min Act: 0.0000

Data Index: 1008219 (The Pile)

Max Activating Token Index: 507

Text #12

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2131. Min Act: 0.0000

Data Index: 1455225 (The Pile)

Max Activating Token Index: 529

Text #13

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2114. Min Act: 0.0000

Data Index: 501446 (The Pile)

Max Activating Token Index: 213

Text #14

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2083. Min Act: 0.0000

Data Index: 1397298 (The Pile)

Max Activating Token Index: 374

Text #15

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2061. Min Act: -0.0000

Data Index: 392996 (The Pile)

Max Activating Token Index: 52

Text #16

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2133. Min Act: 0.0000

Data Index: 1203505 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1993. Min Act: 0.0000

Data Index: 1133792 (The Pile)

Max Activating Token Index: 610

Text #18

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2056. Min Act: 0.0000

Data Index: 585217 (The Pile)

Max Activating Token Index: 16

Text #19

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2125. Min Act: 0.0000

Data Index: 11265 (The Pile)

Max Activating Token Index: 40