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

Dataset: The Pile

Neuron 4707 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.4019. Min Act: -0.0000

Data Index: 996332 (The Pile)

Max Activating Token Index: 702

Text #1

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.4650. Min Act: -0.0000

Data Index: 896026 (The Pile)

Max Activating Token Index: 544

Text #2

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.4238. Min Act: -0.0000

Data Index: 252512 (The Pile)

Max Activating Token Index: 335

Text #3

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.2316. Min Act: -0.0000

Data Index: 341427 (The Pile)

Max Activating Token Index: 858

Text #4

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.1759. Min Act: -0.0000

Data Index: 6020 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.1989. Min Act: -0.0000

Data Index: 81949 (The Pile)

Max Activating Token Index: 867

Text #6

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.2854. Min Act: -0.0000

Data Index: 733582 (The Pile)

Max Activating Token Index: 745

Text #7

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.2404. Min Act: -0.0000

Data Index: 1732738 (The Pile)

Max Activating Token Index: 924

Text #8

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.1004. Min Act: -0.0000

Data Index: 1547667 (The Pile)

Max Activating Token Index: 154

Text #9

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.1666. Min Act: -0.0000

Data Index: 1469351 (The Pile)

Max Activating Token Index: 102

Text #10

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.0901. Min Act: -0.0000

Data Index: 1743439 (The Pile)

Max Activating Token Index: 1004

Text #11

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.1611. Min Act: -0.0000

Data Index: 1119385 (The Pile)

Max Activating Token Index: 466

Text #12

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.1154. Min Act: -0.0000

Data Index: 1368376 (The Pile)

Max Activating Token Index: 153

Text #13

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.1191. Min Act: -0.0000

Data Index: 739181 (The Pile)

Max Activating Token Index: 858

Text #14

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.1783. Min Act: -0.0000

Data Index: 20915 (The Pile)

Max Activating Token Index: 908

Text #15

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.1156. Min Act: -0.0000

Data Index: 41119 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.1176. Min Act: -0.0000

Data Index: 359147 (The Pile)

Max Activating Token Index: 152

Text #17

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.0626. Min Act: -0.0000

Data Index: 1074228 (The Pile)

Max Activating Token Index: 409

Text #18

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.0375. Min Act: -0.0000

Data Index: 1943339 (The Pile)

Max Activating Token Index: 301

Text #19

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.0080. Min Act: -0.0000

Data Index: 1802341 (The Pile)

Max Activating Token Index: 508