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

Dataset: The Pile

Neuron 107 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7747. Min Act: -0.0000

Data Index: 1503362 (The Pile)

Max Activating Token Index: 271

Text #1

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1994489 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1014966 (The Pile)

Max Activating Token Index: 169

Text #3

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1393468 (The Pile)

Max Activating Token Index: 179

Text #4

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7235. Min Act: -0.0000

Data Index: 370930 (The Pile)

Max Activating Token Index: 265

Text #5

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.6915. Min Act: -0.0000

Data Index: 565736 (The Pile)

Max Activating Token Index: 298

Text #6

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1902897 (The Pile)

Max Activating Token Index: 275

Text #7

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1086778 (The Pile)

Max Activating Token Index: 249

Text #8

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1316665 (The Pile)

Max Activating Token Index: 412

Text #9

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1736198 (The Pile)

Max Activating Token Index: 205

Text #10

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.6724. Min Act: -0.0000

Data Index: 355536 (The Pile)

Max Activating Token Index: 196

Text #11

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.6749. Min Act: -0.0000

Data Index: 1290639 (The Pile)

Max Activating Token Index: 623

Text #12

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1031944 (The Pile)

Max Activating Token Index: 201

Text #13

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1786495 (The Pile)

Max Activating Token Index: 144

Text #14

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.5937. Min Act: -0.0000

Data Index: 902061 (The Pile)

Max Activating Token Index: 209

Text #15

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.6415. Min Act: -0.0000

Data Index: 1248308 (The Pile)

Max Activating Token Index: 135

Text #16

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.6303. Min Act: -0.0001

Data Index: 977793 (The Pile)

Max Activating Token Index: 291

Text #17

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.6846. Min Act: -0.0000

Data Index: 660157 (The Pile)

Max Activating Token Index: 265

Text #18

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1300481 (The Pile)

Max Activating Token Index: 231

Text #19

Max Range: 0.7747. Min Range: -0.7747

Max Act: 0.6664. Min Act: -0.0000

Data Index: 646593 (The Pile)

Max Activating Token Index: 246