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

Dataset: The Pile

Neuron 1495 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: 0.0150. Min Range: -0.0150

Max Act: 0.0150. Min Act: -0.0000

Data Index: 1325109 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0144. Min Act: -0.0000

Data Index: 63297 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0142. Min Act: -0.0000

Data Index: 1383343 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0141. Min Act: -0.0000

Data Index: 1917303 (The Pile)

Max Activating Token Index: 1019

Text #4

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0140. Min Act: 0.0000

Data Index: 383895 (The Pile)

Max Activating Token Index: 1014

Text #5

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0140. Min Act: 0.0000

Data Index: 616163 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0139. Min Act: -0.0000

Data Index: 1220292 (The Pile)

Max Activating Token Index: 1010

Text #7

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0138. Min Act: 0.0000

Data Index: 720609 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0138. Min Act: -0.0000

Data Index: 1189203 (The Pile)

Max Activating Token Index: 998

Text #9

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0137. Min Act: -0.0000

Data Index: 1791370 (The Pile)

Max Activating Token Index: 1009

Text #10

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0137. Min Act: -0.0000

Data Index: 597640 (The Pile)

Max Activating Token Index: 1005

Text #11

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0137. Min Act: -0.0000

Data Index: 1017475 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0136. Min Act: -0.0000

Data Index: 1538954 (The Pile)

Max Activating Token Index: 1021

Text #13

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0139. Min Act: -0.0000

Data Index: 374499 (The Pile)

Max Activating Token Index: 1020

Text #14

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0131. Min Act: -0.0000

Data Index: 1324760 (The Pile)

Max Activating Token Index: 1017

Text #15

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0136. Min Act: -0.0000

Data Index: 880591 (The Pile)

Max Activating Token Index: 1019

Text #16

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0135. Min Act: -0.0000

Data Index: 1659982 (The Pile)

Max Activating Token Index: 1019

Text #17

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0134. Min Act: -0.0000

Data Index: 826765 (The Pile)

Max Activating Token Index: 1013

Text #18

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0134. Min Act: 0.0000

Data Index: 73634 (The Pile)

Max Activating Token Index: 1002

Text #19

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0133. Min Act: -0.0000

Data Index: 1773371 (The Pile)

Max Activating Token Index: 1009