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

Dataset: The Pile

Neuron 1585 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.4252. Min Act: -0.0000

Data Index: 1269406 (The Pile)

Max Activating Token Index: 18

Text #1

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.3649. Min Act: -0.0000

Data Index: 959409 (The Pile)

Max Activating Token Index: 657

Text #2

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.3976. Min Act: -0.0000

Data Index: 1500140 (The Pile)

Max Activating Token Index: 993

Text #3

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.3120. Min Act: -0.0000

Data Index: 1079955 (The Pile)

Max Activating Token Index: 195

Text #4

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.3113. Min Act: -0.0000

Data Index: 1272098 (The Pile)

Max Activating Token Index: 882

Text #5

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.2738. Min Act: -0.0000

Data Index: 1224958 (The Pile)

Max Activating Token Index: 937

Text #6

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.1907. Min Act: -0.0000

Data Index: 469611 (The Pile)

Max Activating Token Index: 131

Text #7

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.3155. Min Act: -0.0000

Data Index: 1409927 (The Pile)

Max Activating Token Index: 184

Text #8

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.1605. Min Act: -0.0000

Data Index: 974987 (The Pile)

Max Activating Token Index: 570

Text #9

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.2099. Min Act: -0.0000

Data Index: 1782190 (The Pile)

Max Activating Token Index: 938

Text #10

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.1393. Min Act: -0.0000

Data Index: 651267 (The Pile)

Max Activating Token Index: 178

Text #11

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.1993. Min Act: -0.0000

Data Index: 1194381 (The Pile)

Max Activating Token Index: 419

Text #12

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.1316. Min Act: -0.0000

Data Index: 639641 (The Pile)

Max Activating Token Index: 393

Text #13

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.1539. Min Act: -0.0000

Data Index: 156580 (The Pile)

Max Activating Token Index: 411

Text #14

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.1828. Min Act: -0.0000

Data Index: 1740369 (The Pile)

Max Activating Token Index: 957

Text #15

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.1856. Min Act: 0.0000

Data Index: 782167 (The Pile)

Max Activating Token Index: 651

Text #16

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.0992. Min Act: -0.0000

Data Index: 1412983 (The Pile)

Max Activating Token Index: 206

Text #17

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.1839. Min Act: -0.0000

Data Index: 50501 (The Pile)

Max Activating Token Index: 638

Text #18

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.2168. Min Act: -0.0000

Data Index: 1797385 (The Pile)

Max Activating Token Index: 786

Text #19

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.1529. Min Act: -0.0000

Data Index: 1355174 (The Pile)

Max Activating Token Index: 940