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

Dataset: The Pile

Neuron 5041 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: 0.0143. Min Range: -0.0143

Max Act: 0.0142. Min Act: -0.0000

Data Index: 776591 (The Pile)

Max Activating Token Index: 969

Text #1

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0143. Min Act: -0.0000

Data Index: 1406701 (The Pile)

Max Activating Token Index: 927

Text #2

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0140. Min Act: -0.0000

Data Index: 1110955 (The Pile)

Max Activating Token Index: 830

Text #3

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0137. Min Act: -0.0000

Data Index: 1805051 (The Pile)

Max Activating Token Index: 888

Text #4

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0137. Min Act: -0.0000

Data Index: 697876 (The Pile)

Max Activating Token Index: 838

Text #5

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0137. Min Act: -0.0000

Data Index: 558445 (The Pile)

Max Activating Token Index: 1004

Text #6

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0136. Min Act: -0.0000

Data Index: 904169 (The Pile)

Max Activating Token Index: 935

Text #7

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0135. Min Act: -0.0000

Data Index: 1617925 (The Pile)

Max Activating Token Index: 905

Text #8

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0134. Min Act: -0.0000

Data Index: 1566007 (The Pile)

Max Activating Token Index: 919

Text #9

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0134. Min Act: -0.0000

Data Index: 1914289 (The Pile)

Max Activating Token Index: 936

Text #10

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0133. Min Act: -0.0000

Data Index: 982220 (The Pile)

Max Activating Token Index: 960

Text #11

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0132. Min Act: -0.0000

Data Index: 247527 (The Pile)

Max Activating Token Index: 825

Text #12

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0131. Min Act: -0.0000

Data Index: 1532396 (The Pile)

Max Activating Token Index: 764

Text #13

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0131. Min Act: -0.0000

Data Index: 1378153 (The Pile)

Max Activating Token Index: 899

Text #14

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0131. Min Act: -0.0000

Data Index: 150826 (The Pile)

Max Activating Token Index: 937

Text #15

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0131. Min Act: -0.0000

Data Index: 1960099 (The Pile)

Max Activating Token Index: 923

Text #16

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0130. Min Act: -0.0000

Data Index: 1715813 (The Pile)

Max Activating Token Index: 841

Text #17

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0130. Min Act: -0.0000

Data Index: 1928468 (The Pile)

Max Activating Token Index: 1016

Text #18

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0135. Min Act: -0.0000

Data Index: 289579 (The Pile)

Max Activating Token Index: 863

Text #19

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0130. Min Act: -0.0000

Data Index: 1609635 (The Pile)

Max Activating Token Index: 807