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

Dataset: The Pile

Neuron 1217 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.7428. Min Act: -0.0000

Data Index: 298205 (The Pile)

Max Activating Token Index: 910

Text #1

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.7855. Min Act: -0.0000

Data Index: 853436 (The Pile)

Max Activating Token Index: 996

Text #2

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.7435. Min Act: -0.0000

Data Index: 631759 (The Pile)

Max Activating Token Index: 704

Text #3

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1128060 (The Pile)

Max Activating Token Index: 440

Text #4

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.7167. Min Act: -0.0000

Data Index: 1435608 (The Pile)

Max Activating Token Index: 984

Text #5

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1237299 (The Pile)

Max Activating Token Index: 249

Text #6

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6917. Min Act: -0.0000

Data Index: 997719 (The Pile)

Max Activating Token Index: 769

Text #7

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6781. Min Act: -0.0000

Data Index: 418748 (The Pile)

Max Activating Token Index: 527

Text #8

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6996. Min Act: 0.0000

Data Index: 1112017 (The Pile)

Max Activating Token Index: 426

Text #9

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6654. Min Act: -0.0000

Data Index: 590138 (The Pile)

Max Activating Token Index: 274

Text #10

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1851427 (The Pile)

Max Activating Token Index: 898

Text #11

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6553. Min Act: -0.0000

Data Index: 1583641 (The Pile)

Max Activating Token Index: 976

Text #12

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6544. Min Act: -0.0000

Data Index: 17647 (The Pile)

Max Activating Token Index: 841

Text #13

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6325. Min Act: -0.0000

Data Index: 334974 (The Pile)

Max Activating Token Index: 984

Text #14

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6288. Min Act: -0.0000

Data Index: 1119874 (The Pile)

Max Activating Token Index: 652

Text #15

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6054. Min Act: -0.0000

Data Index: 1485166 (The Pile)

Max Activating Token Index: 1006

Text #16

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1871544 (The Pile)

Max Activating Token Index: 254

Text #17

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6015. Min Act: -0.0000

Data Index: 878698 (The Pile)

Max Activating Token Index: 249

Text #18

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1463334 (The Pile)

Max Activating Token Index: 778

Text #19

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6179. Min Act: -0.0000

Data Index: 1284238 (The Pile)

Max Activating Token Index: 1003