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

Dataset: The Pile

Neuron 1128 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: 0.0158. Min Range: -0.0158

Max Act: 0.0158. Min Act: -0.0000

Data Index: 259734 (The Pile)

Max Activating Token Index: 1020

Text #1

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0148. Min Act: -0.0000

Data Index: 1682756 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0150. Min Act: -0.0000

Data Index: 1802982 (The Pile)

Max Activating Token Index: 665

Text #3

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0141. Min Act: -0.0000

Data Index: 1181663 (The Pile)

Max Activating Token Index: 984

Text #4

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0143. Min Act: -0.0000

Data Index: 68353 (The Pile)

Max Activating Token Index: 833

Text #5

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0142. Min Act: -0.0000

Data Index: 1971422 (The Pile)

Max Activating Token Index: 1012

Text #6

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0142. Min Act: 0.0000

Data Index: 1397221 (The Pile)

Max Activating Token Index: 910

Text #7

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0141. Min Act: -0.0000

Data Index: 1754013 (The Pile)

Max Activating Token Index: 962

Text #8

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0141. Min Act: -0.0000

Data Index: 654655 (The Pile)

Max Activating Token Index: 444

Text #9

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0141. Min Act: -0.0000

Data Index: 1052829 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0141. Min Act: 0.0000

Data Index: 321722 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0140. Min Act: -0.0000

Data Index: 395885 (The Pile)

Max Activating Token Index: 1022

Text #12

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0140. Min Act: -0.0000

Data Index: 1850203 (The Pile)

Max Activating Token Index: 1019

Text #13

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0139. Min Act: -0.0000

Data Index: 638196 (The Pile)

Max Activating Token Index: 993

Text #14

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0138. Min Act: -0.0000

Data Index: 1282856 (The Pile)

Max Activating Token Index: 623

Text #15

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0137. Min Act: -0.0000

Data Index: 1980411 (The Pile)

Max Activating Token Index: 972

Text #16

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0137. Min Act: -0.0000

Data Index: 1633460 (The Pile)

Max Activating Token Index: 723

Text #17

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0141. Min Act: 0.0000

Data Index: 866362 (The Pile)

Max Activating Token Index: 885

Text #18

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0136. Min Act: 0.0000

Data Index: 432098 (The Pile)

Max Activating Token Index: 977

Text #19

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0136. Min Act: -0.0000

Data Index: 1974196 (The Pile)

Max Activating Token Index: 891