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

Dataset: The Pile

Neuron 2417 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1456919 (The Pile)

Max Activating Token Index: 718

Text #1

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3450. Min Act: -0.0000

Data Index: 979093 (The Pile)

Max Activating Token Index: 877

Text #2

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3267. Min Act: -0.0000

Data Index: 215826 (The Pile)

Max Activating Token Index: 101

Text #3

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1242072 (The Pile)

Max Activating Token Index: 1016

Text #4

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1433414 (The Pile)

Max Activating Token Index: 981

Text #5

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3014. Min Act: 0.0000

Data Index: 635171 (The Pile)

Max Activating Token Index: 716

Text #6

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3039. Min Act: -0.0000

Data Index: 1185449 (The Pile)

Max Activating Token Index: 668

Text #7

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3220. Min Act: -0.0000

Data Index: 590238 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2969. Min Act: -0.0000

Data Index: 637090 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3130. Min Act: -0.0000

Data Index: 179540 (The Pile)

Max Activating Token Index: 267

Text #10

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3011. Min Act: -0.0000

Data Index: 516740 (The Pile)

Max Activating Token Index: 297

Text #11

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1712406 (The Pile)

Max Activating Token Index: 351

Text #12

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2999. Min Act: 0.0000

Data Index: 487602 (The Pile)

Max Activating Token Index: 928

Text #13

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2968. Min Act: -0.0000

Data Index: 1543826 (The Pile)

Max Activating Token Index: 888

Text #14

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2768. Min Act: -0.0000

Data Index: 1111869 (The Pile)

Max Activating Token Index: 579

Text #15

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2804. Min Act: -0.0000

Data Index: 1960559 (The Pile)

Max Activating Token Index: 430

Text #16

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2794. Min Act: 0.0000

Data Index: 401009 (The Pile)

Max Activating Token Index: 833

Text #17

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1947326 (The Pile)

Max Activating Token Index: 245

Text #18

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2823. Min Act: -0.0000

Data Index: 889744 (The Pile)

Max Activating Token Index: 901

Text #19

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1389501 (The Pile)

Max Activating Token Index: 570