Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3809 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.2131. Min Act: -0.0000

Data Index: 550916 (The Pile)

Max Activating Token Index: 640

Text #1

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1513780 (The Pile)

Max Activating Token Index: 32

Text #2

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1651. Min Act: -0.0000

Data Index: 270295 (The Pile)

Max Activating Token Index: 193

Text #3

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1490. Min Act: -0.0000

Data Index: 1186710 (The Pile)

Max Activating Token Index: 161

Text #4

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1327. Min Act: -0.0000

Data Index: 1404724 (The Pile)

Max Activating Token Index: 933

Text #5

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1391. Min Act: -0.0000

Data Index: 1210653 (The Pile)

Max Activating Token Index: 185

Text #6

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1313. Min Act: -0.0000

Data Index: 53143 (The Pile)

Max Activating Token Index: 113

Text #7

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1551. Min Act: -0.0000

Data Index: 137332 (The Pile)

Max Activating Token Index: 937

Text #8

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1125. Min Act: -0.0000

Data Index: 321227 (The Pile)

Max Activating Token Index: 61

Text #9

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1314. Min Act: -0.0000

Data Index: 749556 (The Pile)

Max Activating Token Index: 568

Text #10

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1698043 (The Pile)

Max Activating Token Index: 199

Text #11

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1128. Min Act: -0.0000

Data Index: 578512 (The Pile)

Max Activating Token Index: 989

Text #12

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1053. Min Act: -0.0000

Data Index: 1678380 (The Pile)

Max Activating Token Index: 314

Text #13

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1079. Min Act: -0.0000

Data Index: 441282 (The Pile)

Max Activating Token Index: 465

Text #14

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1056. Min Act: -0.0000

Data Index: 500234 (The Pile)

Max Activating Token Index: 881

Text #15

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1078. Min Act: -0.0000

Data Index: 308631 (The Pile)

Max Activating Token Index: 395

Text #16

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1827223 (The Pile)

Max Activating Token Index: 380

Text #17

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1368672 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.0981. Min Act: -0.0000

Data Index: 875510 (The Pile)

Max Activating Token Index: 928

Text #19

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1284357 (The Pile)

Max Activating Token Index: 96