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

Dataset: The Pile

Neuron 50 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.9980. Min Act: -0.0000

Data Index: 99809 (The Pile)

Max Activating Token Index: 431

Text #1

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.3567. Min Act: -0.0000

Data Index: 259110 (The Pile)

Max Activating Token Index: 38

Text #2

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.4221. Min Act: -0.0000

Data Index: 1865015 (The Pile)

Max Activating Token Index: 6

Text #3

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.3265. Min Act: -0.0000

Data Index: 1757037 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.3160. Min Act: -0.0000

Data Index: 91407 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.2651. Min Act: -0.0000

Data Index: 544783 (The Pile)

Max Activating Token Index: 830

Text #6

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.4328. Min Act: -0.0000

Data Index: 885925 (The Pile)

Max Activating Token Index: 661

Text #7

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.4009. Min Act: -0.0000

Data Index: 718419 (The Pile)

Max Activating Token Index: 57

Text #8

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.2845. Min Act: -0.0000

Data Index: 45559 (The Pile)

Max Activating Token Index: 657

Text #9

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.3183. Min Act: -0.0000

Data Index: 1303526 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.2083. Min Act: -0.0000

Data Index: 1215847 (The Pile)

Max Activating Token Index: 88

Text #11

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.1740. Min Act: -0.0000

Data Index: 796657 (The Pile)

Max Activating Token Index: 924

Text #12

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.2985. Min Act: -0.0000

Data Index: 310066 (The Pile)

Max Activating Token Index: 19

Text #13

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.2030. Min Act: -0.0000

Data Index: 736056 (The Pile)

Max Activating Token Index: 972

Text #14

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.1779. Min Act: -0.0000

Data Index: 1164004 (The Pile)

Max Activating Token Index: 443

Text #15

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.0895. Min Act: -0.0000

Data Index: 1025270 (The Pile)

Max Activating Token Index: 544

Text #16

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.1124. Min Act: -0.0000

Data Index: 235966 (The Pile)

Max Activating Token Index: 899

Text #17

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.2570. Min Act: -0.0000

Data Index: 1687499 (The Pile)

Max Activating Token Index: 126

Text #18

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.1286. Min Act: -0.0000

Data Index: 673533 (The Pile)

Max Activating Token Index: 167

Text #19

Max Range: 1.9980. Min Range: -1.9980

Max Act: 1.2214. Min Act: -0.0000

Data Index: 859576 (The Pile)

Max Activating Token Index: 8