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

Dataset: The Pile

Neuron 1239 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.3530. Min Act: -0.0000

Data Index: 910516 (The Pile)

Max Activating Token Index: 730

Text #1

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2973. Min Act: -0.0000

Data Index: 419043 (The Pile)

Max Activating Token Index: 695

Text #2

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2372. Min Act: -0.0000

Data Index: 19910 (The Pile)

Max Activating Token Index: 939

Text #3

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2527. Min Act: -0.0000

Data Index: 388092 (The Pile)

Max Activating Token Index: 179

Text #4

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1703462 (The Pile)

Max Activating Token Index: 823

Text #5

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2407. Min Act: -0.0000

Data Index: 75753 (The Pile)

Max Activating Token Index: 512

Text #6

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2433. Min Act: -0.0000

Data Index: 586509 (The Pile)

Max Activating Token Index: 479

Text #7

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2290. Min Act: -0.0000

Data Index: 1746757 (The Pile)

Max Activating Token Index: 142

Text #8

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2201. Min Act: -0.0000

Data Index: 845334 (The Pile)

Max Activating Token Index: 283

Text #9

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2479. Min Act: -0.0000

Data Index: 1081568 (The Pile)

Max Activating Token Index: 167

Text #10

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1617319 (The Pile)

Max Activating Token Index: 717

Text #11

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2439. Min Act: -0.0000

Data Index: 970445 (The Pile)

Max Activating Token Index: 1001

Text #12

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2174. Min Act: -0.0000

Data Index: 1153167 (The Pile)

Max Activating Token Index: 128

Text #13

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1657631 (The Pile)

Max Activating Token Index: 762

Text #14

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2324. Min Act: -0.0000

Data Index: 1999976 (The Pile)

Max Activating Token Index: 986

Text #15

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2138. Min Act: -0.0000

Data Index: 1660680 (The Pile)

Max Activating Token Index: 762

Text #16

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2066. Min Act: -0.0000

Data Index: 661841 (The Pile)

Max Activating Token Index: 49

Text #17

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2055. Min Act: -0.0000

Data Index: 546821 (The Pile)

Max Activating Token Index: 961

Text #18

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1830927 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2061. Min Act: -0.0000

Data Index: 786718 (The Pile)

Max Activating Token Index: 215