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

Dataset: The Pile

Neuron 89 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.2935. Min Act: -0.0000

Data Index: 512321 (The Pile)

Max Activating Token Index: 923

Text #1

Max Range: 5.4232. Min Range: -5.4232

Max Act: 4.6948. Min Act: -0.0000

Data Index: 1606455 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.1980. Min Act: -0.0000

Data Index: 1891124 (The Pile)

Max Activating Token Index: 743

Text #3

Max Range: 5.4232. Min Range: -5.4232

Max Act: 4.8048. Min Act: -0.0000

Data Index: 23663 (The Pile)

Max Activating Token Index: 414

Text #4

Max Range: 5.4232. Min Range: -5.4232

Max Act: 4.7089. Min Act: -0.0000

Data Index: 883808 (The Pile)

Max Activating Token Index: 322

Text #5

Max Range: 5.4232. Min Range: -5.4232

Max Act: 4.8872. Min Act: -0.0000

Data Index: 1623114 (The Pile)

Max Activating Token Index: 495

Text #6

Max Range: 5.4232. Min Range: -5.4232

Max Act: 4.6808. Min Act: -0.0000

Data Index: 1609078 (The Pile)

Max Activating Token Index: 977

Text #7

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.1731. Min Act: -0.0000

Data Index: 1906470 (The Pile)

Max Activating Token Index: 602

Text #8

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.1374. Min Act: -0.0000

Data Index: 1535099 (The Pile)

Max Activating Token Index: 172

Text #9

Max Range: 5.4232. Min Range: -5.4232

Max Act: 4.6274. Min Act: -0.0000

Data Index: 1725792 (The Pile)

Max Activating Token Index: 939

Text #10

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.4232. Min Act: -0.0000

Data Index: 1204285 (The Pile)

Max Activating Token Index: 1007

Text #11

Max Range: 5.4232. Min Range: -5.4232

Max Act: 4.5363. Min Act: -0.0000

Data Index: 343833 (The Pile)

Max Activating Token Index: 406

Text #12

Max Range: 5.4232. Min Range: -5.4232

Max Act: 4.7191. Min Act: -0.0000

Data Index: 1375605 (The Pile)

Max Activating Token Index: 798

Text #13

Max Range: 5.4232. Min Range: -5.4232

Max Act: 4.7470. Min Act: -0.0000

Data Index: 1316629 (The Pile)

Max Activating Token Index: 463

Text #14

Max Range: 5.4232. Min Range: -5.4232

Max Act: 4.6550. Min Act: -0.0000

Data Index: 1098177 (The Pile)

Max Activating Token Index: 565

Text #15

Max Range: 5.4232. Min Range: -5.4232

Max Act: 4.4408. Min Act: -0.0000

Data Index: 722246 (The Pile)

Max Activating Token Index: 527

Text #16

Max Range: 5.4232. Min Range: -5.4232

Max Act: 4.0897. Min Act: -0.0000

Data Index: 1915441 (The Pile)

Max Activating Token Index: 598

Text #17

Max Range: 5.4232. Min Range: -5.4232

Max Act: 4.6363. Min Act: -0.0000

Data Index: 1354710 (The Pile)

Max Activating Token Index: 410

Text #18

Max Range: 5.4232. Min Range: -5.4232

Max Act: 4.4732. Min Act: -0.0000

Data Index: 1646988 (The Pile)

Max Activating Token Index: 827

Text #19

Max Range: 5.4232. Min Range: -5.4232

Max Act: 4.6563. Min Act: -0.0000

Data Index: 1130630 (The Pile)

Max Activating Token Index: 890