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

Dataset: The Pile

Neuron 3685 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: 1.9877. Min Range: -1.9877

Max Act: 1.9877. Min Act: -0.0000

Data Index: 157336 (The Pile)

Max Activating Token Index: 883

Text #1

Max Range: 1.9877. Min Range: -1.9877

Max Act: 1.9568. Min Act: -0.0000

Data Index: 1424129 (The Pile)

Max Activating Token Index: 800

Text #2

Max Range: 1.9877. Min Range: -1.9877

Max Act: 1.9125. Min Act: -0.0000

Data Index: 1790943 (The Pile)

Max Activating Token Index: 618

Text #3

Max Range: 1.9877. Min Range: -1.9877

Max Act: 1.9419. Min Act: -0.0000

Data Index: 211034 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 1.9877. Min Range: -1.9877

Max Act: 1.9314. Min Act: -0.0000

Data Index: 894760 (The Pile)

Max Activating Token Index: 126

Text #5

Max Range: 1.9877. Min Range: -1.9877

Max Act: 1.6911. Min Act: -0.0000

Data Index: 1100882 (The Pile)

Max Activating Token Index: 384

Text #6

Max Range: 1.9877. Min Range: -1.9877

Max Act: 1.7673. Min Act: -0.0000

Data Index: 838592 (The Pile)

Max Activating Token Index: 516

Text #7

Max Range: 1.9877. Min Range: -1.9877

Max Act: 1.6858. Min Act: -0.0000

Data Index: 1725932 (The Pile)

Max Activating Token Index: 306

Text #8

Max Range: 1.9877. Min Range: -1.9877

Max Act: 1.7164. Min Act: -0.0000

Data Index: 1371806 (The Pile)

Max Activating Token Index: 690

Text #9

Max Range: 1.9877. Min Range: -1.9877

Max Act: 1.6719. Min Act: -0.0000

Data Index: 125903 (The Pile)

Max Activating Token Index: 203

Text #10

Max Range: 1.9877. Min Range: -1.9877

Max Act: 1.5565. Min Act: -0.0000

Data Index: 1132712 (The Pile)

Max Activating Token Index: 810

Text #11

Max Range: 1.9877. Min Range: -1.9877

Max Act: 1.4128. Min Act: -0.0000

Data Index: 1455449 (The Pile)

Max Activating Token Index: 964

Text #12

Max Range: 1.9877. Min Range: -1.9877

Max Act: 1.5706. Min Act: -0.0000

Data Index: 1331150 (The Pile)

Max Activating Token Index: 915

Text #13

Max Range: 1.9877. Min Range: -1.9877

Max Act: 1.4145. Min Act: -0.0000

Data Index: 467266 (The Pile)

Max Activating Token Index: 254

Text #14

Max Range: 1.9877. Min Range: -1.9877

Max Act: 1.4624. Min Act: -0.0000

Data Index: 1461321 (The Pile)

Max Activating Token Index: 731

Text #15

Max Range: 1.9877. Min Range: -1.9877

Max Act: 1.4601. Min Act: -0.0000

Data Index: 436406 (The Pile)

Max Activating Token Index: 811

Text #16

Max Range: 1.9877. Min Range: -1.9877

Max Act: 1.4039. Min Act: -0.0000

Data Index: 1365370 (The Pile)

Max Activating Token Index: 632

Text #17

Max Range: 1.9877. Min Range: -1.9877

Max Act: 1.5260. Min Act: -0.0000

Data Index: 480702 (The Pile)

Max Activating Token Index: 325

Text #18

Max Range: 1.9877. Min Range: -1.9877

Max Act: 1.4306. Min Act: -0.0000

Data Index: 330234 (The Pile)

Max Activating Token Index: 279

Text #19

Max Range: 1.9877. Min Range: -1.9877

Max Act: 1.4241. Min Act: -0.0000

Data Index: 992781 (The Pile)

Max Activating Token Index: 649