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

Dataset: The Pile

Neuron 4196 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.6993. Min Act: -0.0000

Data Index: 1620711 (The Pile)

Max Activating Token Index: 88

Text #1

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5987. Min Act: -0.0000

Data Index: 222999 (The Pile)

Max Activating Token Index: 334

Text #2

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.6150. Min Act: -0.0000

Data Index: 1566811 (The Pile)

Max Activating Token Index: 453

Text #3

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.6613. Min Act: -0.0000

Data Index: 837428 (The Pile)

Max Activating Token Index: 978

Text #4

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.6050. Min Act: -0.0000

Data Index: 795023 (The Pile)

Max Activating Token Index: 168

Text #5

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1147460 (The Pile)

Max Activating Token Index: 830

Text #6

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.6153. Min Act: -0.0000

Data Index: 535970 (The Pile)

Max Activating Token Index: 491

Text #7

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5586. Min Act: -0.0000

Data Index: 656074 (The Pile)

Max Activating Token Index: 211

Text #8

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5669. Min Act: -0.0000

Data Index: 1854373 (The Pile)

Max Activating Token Index: 877

Text #9

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1542155 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5703. Min Act: -0.0000

Data Index: 528811 (The Pile)

Max Activating Token Index: 475

Text #11

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5543. Min Act: -0.0000

Data Index: 159532 (The Pile)

Max Activating Token Index: 158

Text #12

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5368. Min Act: -0.0000

Data Index: 847993 (The Pile)

Max Activating Token Index: 719

Text #13

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1279454 (The Pile)

Max Activating Token Index: 556

Text #14

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5324. Min Act: -0.0000

Data Index: 164595 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5128. Min Act: -0.0000

Data Index: 910811 (The Pile)

Max Activating Token Index: 764

Text #16

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1039231 (The Pile)

Max Activating Token Index: 959

Text #17

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5319. Min Act: -0.0000

Data Index: 1317763 (The Pile)

Max Activating Token Index: 546

Text #18

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5176. Min Act: -0.0000

Data Index: 835866 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5240. Min Act: -0.0000

Data Index: 1990523 (The Pile)

Max Activating Token Index: 997