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

Dataset: The Pile

Neuron 4516 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: 5.2897. Min Range: -5.2897

Max Act: 5.0303. Min Act: -0.0000

Data Index: 968 (The Pile)

Max Activating Token Index: 530

Text #1

Max Range: 5.2897. Min Range: -5.2897

Max Act: 5.1206. Min Act: -0.0000

Data Index: 1999643 (The Pile)

Max Activating Token Index: 936

Text #2

Max Range: 5.2897. Min Range: -5.2897

Max Act: 5.0477. Min Act: -0.0000

Data Index: 471136 (The Pile)

Max Activating Token Index: 571

Text #3

Max Range: 5.2897. Min Range: -5.2897

Max Act: 5.2897. Min Act: -0.0000

Data Index: 1464850 (The Pile)

Max Activating Token Index: 741

Text #4

Max Range: 5.2897. Min Range: -5.2897

Max Act: 4.8081. Min Act: -0.0000

Data Index: 1020324 (The Pile)

Max Activating Token Index: 974

Text #5

Max Range: 5.2897. Min Range: -5.2897

Max Act: 4.8565. Min Act: -0.0000

Data Index: 1386981 (The Pile)

Max Activating Token Index: 622

Text #6

Max Range: 5.2897. Min Range: -5.2897

Max Act: 5.1949. Min Act: -0.0000

Data Index: 1828608 (The Pile)

Max Activating Token Index: 234

Text #7

Max Range: 5.2897. Min Range: -5.2897

Max Act: 4.6225. Min Act: -0.0000

Data Index: 405587 (The Pile)

Max Activating Token Index: 240

Text #8

Max Range: 5.2897. Min Range: -5.2897

Max Act: 4.9955. Min Act: -0.0000

Data Index: 1172820 (The Pile)

Max Activating Token Index: 624

Text #9

Max Range: 5.2897. Min Range: -5.2897

Max Act: 4.9328. Min Act: -0.0000

Data Index: 977058 (The Pile)

Max Activating Token Index: 846

Text #10

Max Range: 5.2897. Min Range: -5.2897

Max Act: 4.6183. Min Act: -0.0000

Data Index: 1387386 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 5.2897. Min Range: -5.2897

Max Act: 4.6004. Min Act: -0.0000

Data Index: 1837912 (The Pile)

Max Activating Token Index: 976

Text #12

Max Range: 5.2897. Min Range: -5.2897

Max Act: 4.5141. Min Act: -0.0000

Data Index: 981337 (The Pile)

Max Activating Token Index: 812

Text #13

Max Range: 5.2897. Min Range: -5.2897

Max Act: 4.6738. Min Act: -0.0000

Data Index: 522211 (The Pile)

Max Activating Token Index: 490

Text #14

Max Range: 5.2897. Min Range: -5.2897

Max Act: 4.5367. Min Act: -0.0000

Data Index: 1116954 (The Pile)

Max Activating Token Index: 832

Text #15

Max Range: 5.2897. Min Range: -5.2897

Max Act: 4.6379. Min Act: -0.0000

Data Index: 1606497 (The Pile)

Max Activating Token Index: 834

Text #16

Max Range: 5.2897. Min Range: -5.2897

Max Act: 4.5879. Min Act: -0.0000

Data Index: 1897988 (The Pile)

Max Activating Token Index: 579

Text #17

Max Range: 5.2897. Min Range: -5.2897

Max Act: 4.7239. Min Act: -0.0000

Data Index: 1143465 (The Pile)

Max Activating Token Index: 187

Text #18

Max Range: 5.2897. Min Range: -5.2897

Max Act: 4.6948. Min Act: -0.0000

Data Index: 718469 (The Pile)

Max Activating Token Index: 739

Text #19

Max Range: 5.2897. Min Range: -5.2897

Max Act: 4.2240. Min Act: -0.0000

Data Index: 316195 (The Pile)

Max Activating Token Index: 762