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

Dataset: The Pile

Neuron 4540 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1641. Min Act: -0.0000

Data Index: 882188 (The Pile)

Max Activating Token Index: 568

Text #1

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1353. Min Act: -0.0000

Data Index: 771419 (The Pile)

Max Activating Token Index: 205

Text #2

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1494. Min Act: -0.0000

Data Index: 939530 (The Pile)

Max Activating Token Index: 674

Text #3

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1324. Min Act: -0.0000

Data Index: 969758 (The Pile)

Max Activating Token Index: 607

Text #4

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1201557 (The Pile)

Max Activating Token Index: 111

Text #5

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1233. Min Act: -0.0000

Data Index: 1295008 (The Pile)

Max Activating Token Index: 264

Text #6

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1247. Min Act: -0.0000

Data Index: 1120145 (The Pile)

Max Activating Token Index: 803

Text #7

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1257. Min Act: -0.0000

Data Index: 459733 (The Pile)

Max Activating Token Index: 306

Text #8

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1203. Min Act: -0.0000

Data Index: 30172 (The Pile)

Max Activating Token Index: 618

Text #9

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1188. Min Act: -0.0000

Data Index: 560748 (The Pile)

Max Activating Token Index: 487

Text #10

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1268. Min Act: -0.0000

Data Index: 157959 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1221. Min Act: -0.0000

Data Index: 1863759 (The Pile)

Max Activating Token Index: 28

Text #12

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1165. Min Act: -0.0000

Data Index: 1247833 (The Pile)

Max Activating Token Index: 213

Text #13

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1207. Min Act: -0.0000

Data Index: 22687 (The Pile)

Max Activating Token Index: 215

Text #14

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1231. Min Act: -0.0000

Data Index: 1711026 (The Pile)

Max Activating Token Index: 278

Text #15

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1134. Min Act: -0.0000

Data Index: 912075 (The Pile)

Max Activating Token Index: 576

Text #16

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1177. Min Act: -0.0000

Data Index: 623597 (The Pile)

Max Activating Token Index: 592

Text #17

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1105. Min Act: 0.0000

Data Index: 1548932 (The Pile)

Max Activating Token Index: 318

Text #18

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1055. Min Act: -0.0000

Data Index: 294232 (The Pile)

Max Activating Token Index: 828

Text #19

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1978427 (The Pile)

Max Activating Token Index: 786