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

Dataset: The Pile

Neuron 1324 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: 0.0194. Min Range: -0.0194

Max Act: 0.0194. Min Act: -0.0000

Data Index: 565220 (The Pile)

Max Activating Token Index: 1014

Text #1

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0171. Min Act: -0.0000

Data Index: 1605093 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0144. Min Act: -0.0000

Data Index: 76567 (The Pile)

Max Activating Token Index: 990

Text #3

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0140. Min Act: -0.0000

Data Index: 1869529 (The Pile)

Max Activating Token Index: 971

Text #4

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0136. Min Act: -0.0000

Data Index: 39978 (The Pile)

Max Activating Token Index: 927

Text #5

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0135. Min Act: 0.0000

Data Index: 1603199 (The Pile)

Max Activating Token Index: 969

Text #6

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0134. Min Act: -0.0000

Data Index: 1984157 (The Pile)

Max Activating Token Index: 966

Text #7

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0134. Min Act: -0.0000

Data Index: 1308496 (The Pile)

Max Activating Token Index: 945

Text #8

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0133. Min Act: -0.0000

Data Index: 1765731 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0134. Min Act: -0.0000

Data Index: 548776 (The Pile)

Max Activating Token Index: 1017

Text #10

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0138. Min Act: -0.0000

Data Index: 484612 (The Pile)

Max Activating Token Index: 930

Text #11

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0132. Min Act: -0.0000

Data Index: 1864976 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0132. Min Act: -0.0000

Data Index: 1478715 (The Pile)

Max Activating Token Index: 828

Text #13

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0131. Min Act: -0.0000

Data Index: 1620061 (The Pile)

Max Activating Token Index: 935

Text #14

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0132. Min Act: -0.0000

Data Index: 328390 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0131. Min Act: -0.0000

Data Index: 1632271 (The Pile)

Max Activating Token Index: 1022

Text #16

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0130. Min Act: 0.0000

Data Index: 1764953 (The Pile)

Max Activating Token Index: 926

Text #17

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0130. Min Act: -0.0000

Data Index: 157778 (The Pile)

Max Activating Token Index: 954

Text #18

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0129. Min Act: 0.0000

Data Index: 374159 (The Pile)

Max Activating Token Index: 1018

Text #19

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0128. Min Act: -0.0000

Data Index: 660634 (The Pile)

Max Activating Token Index: 984