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

Dataset: The Pile

Neuron 674 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: 0.4933. Min Range: -0.4933

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1125785 (The Pile)

Max Activating Token Index: 6

Text #1

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3613. Min Act: -0.0000

Data Index: 1655514 (The Pile)

Max Activating Token Index: 924

Text #2

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3901. Min Act: -0.0000

Data Index: 347863 (The Pile)

Max Activating Token Index: 514

Text #3

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3546. Min Act: -0.0000

Data Index: 471081 (The Pile)

Max Activating Token Index: 1017

Text #4

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3609. Min Act: -0.0000

Data Index: 865755 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3466. Min Act: -0.0000

Data Index: 1162155 (The Pile)

Max Activating Token Index: 803

Text #6

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3721. Min Act: -0.0000

Data Index: 698240 (The Pile)

Max Activating Token Index: 940

Text #7

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3693. Min Act: -0.0000

Data Index: 552040 (The Pile)

Max Activating Token Index: 775

Text #8

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3595. Min Act: -0.0000

Data Index: 1165266 (The Pile)

Max Activating Token Index: 420

Text #9

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3450. Min Act: -0.0000

Data Index: 934593 (The Pile)

Max Activating Token Index: 451

Text #10

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3378. Min Act: -0.0000

Data Index: 1647974 (The Pile)

Max Activating Token Index: 553

Text #11

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3209. Min Act: -0.0000

Data Index: 1775427 (The Pile)

Max Activating Token Index: 8

Text #12

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3311. Min Act: -0.0000

Data Index: 1553078 (The Pile)

Max Activating Token Index: 58

Text #13

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3080. Min Act: -0.0000

Data Index: 856147 (The Pile)

Max Activating Token Index: 976

Text #14

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3289. Min Act: -0.0000

Data Index: 955478 (The Pile)

Max Activating Token Index: 976

Text #15

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3155. Min Act: -0.0000

Data Index: 93777 (The Pile)

Max Activating Token Index: 151

Text #16

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3415. Min Act: -0.0000

Data Index: 1674310 (The Pile)

Max Activating Token Index: 813

Text #17

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3161. Min Act: -0.0000

Data Index: 597009 (The Pile)

Max Activating Token Index: 152

Text #18

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3138. Min Act: -0.0000

Data Index: 101688 (The Pile)

Max Activating Token Index: 465

Text #19

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3088. Min Act: -0.0000

Data Index: 501994 (The Pile)

Max Activating Token Index: 121