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

Dataset: The Pile

Neuron 355 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: 0.0174. Min Range: -0.0174

Max Act: 0.0174. Min Act: -0.0000

Data Index: 686569 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0173. Min Act: -0.0000

Data Index: 683544 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0169. Min Act: -0.0000

Data Index: 1080395 (The Pile)

Max Activating Token Index: 1022

Text #3

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0161. Min Act: -0.0000

Data Index: 1709765 (The Pile)

Max Activating Token Index: 1019

Text #4

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0160. Min Act: -0.0000

Data Index: 1031588 (The Pile)

Max Activating Token Index: 995

Text #5

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0159. Min Act: -0.0000

Data Index: 434987 (The Pile)

Max Activating Token Index: 1018

Text #6

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0155. Min Act: -0.0000

Data Index: 1020087 (The Pile)

Max Activating Token Index: 1002

Text #7

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0149. Min Act: -0.0000

Data Index: 670392 (The Pile)

Max Activating Token Index: 1003

Text #8

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0153. Min Act: -0.0000

Data Index: 27381 (The Pile)

Max Activating Token Index: 1015

Text #9

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0153. Min Act: -0.0000

Data Index: 1420611 (The Pile)

Max Activating Token Index: 1013

Text #10

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0158. Min Act: -0.0000

Data Index: 99204 (The Pile)

Max Activating Token Index: 1021

Text #11

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0152. Min Act: -0.0000

Data Index: 1929480 (The Pile)

Max Activating Token Index: 1010

Text #12

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0151. Min Act: -0.0000

Data Index: 425579 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0151. Min Act: -0.0000

Data Index: 1135411 (The Pile)

Max Activating Token Index: 1005

Text #14

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0156. Min Act: -0.0000

Data Index: 625527 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0151. Min Act: -0.0000

Data Index: 718532 (The Pile)

Max Activating Token Index: 1016

Text #16

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0151. Min Act: -0.0000

Data Index: 1399524 (The Pile)

Max Activating Token Index: 1006

Text #17

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0150. Min Act: -0.0000

Data Index: 1198171 (The Pile)

Max Activating Token Index: 1005

Text #18

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0150. Min Act: -0.0000

Data Index: 406330 (The Pile)

Max Activating Token Index: 993

Text #19

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0149. Min Act: -0.0000

Data Index: 354305 (The Pile)

Max Activating Token Index: 1006