Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1078 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.5532. Min Act: -0.0000

Data Index: 191444 (The Pile)

Max Activating Token Index: 935

Text #1

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.5123. Min Act: -0.0000

Data Index: 714526 (The Pile)

Max Activating Token Index: 768

Text #2

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4739. Min Act: -0.0000

Data Index: 642759 (The Pile)

Max Activating Token Index: 223

Text #3

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4536. Min Act: -0.0000

Data Index: 103698 (The Pile)

Max Activating Token Index: 216

Text #4

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4608. Min Act: -0.0000

Data Index: 507548 (The Pile)

Max Activating Token Index: 820

Text #5

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4094. Min Act: -0.0000

Data Index: 1251570 (The Pile)

Max Activating Token Index: 917

Text #6

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4185. Min Act: -0.0000

Data Index: 418033 (The Pile)

Max Activating Token Index: 865

Text #7

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1135758 (The Pile)

Max Activating Token Index: 896

Text #8

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1709290 (The Pile)

Max Activating Token Index: 949

Text #9

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4490. Min Act: -0.0000

Data Index: 674158 (The Pile)

Max Activating Token Index: 781

Text #10

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4127. Min Act: -0.0000

Data Index: 1710208 (The Pile)

Max Activating Token Index: 725

Text #11

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4217. Min Act: -0.0000

Data Index: 239253 (The Pile)

Max Activating Token Index: 538

Text #12

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1788970 (The Pile)

Max Activating Token Index: 849

Text #13

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3998. Min Act: -0.0000

Data Index: 1948691 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3456. Min Act: -0.0000

Data Index: 1725588 (The Pile)

Max Activating Token Index: 343

Text #15

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3683. Min Act: -0.0000

Data Index: 849628 (The Pile)

Max Activating Token Index: 594

Text #16

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3897. Min Act: -0.0000

Data Index: 981908 (The Pile)

Max Activating Token Index: 412

Text #17

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3422. Min Act: -0.0000

Data Index: 1543035 (The Pile)

Max Activating Token Index: 1016

Text #18

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3505. Min Act: -0.0000

Data Index: 894806 (The Pile)

Max Activating Token Index: 163

Text #19

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3448. Min Act: -0.0000

Data Index: 822961 (The Pile)

Max Activating Token Index: 744