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

Dataset: The Pile

Neuron 3448 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: 3.7386. Min Range: -3.7386

Max Act: 3.6122. Min Act: -0.0000

Data Index: 1225758 (The Pile)

Max Activating Token Index: 704

Text #1

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.5182. Min Act: -0.0000

Data Index: 325350 (The Pile)

Max Activating Token Index: 209

Text #2

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.7386. Min Act: -0.0000

Data Index: 1900229 (The Pile)

Max Activating Token Index: 725

Text #3

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.5123. Min Act: -0.0000

Data Index: 1174879 (The Pile)

Max Activating Token Index: 207

Text #4

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.1792. Min Act: -0.0000

Data Index: 6055 (The Pile)

Max Activating Token Index: 966

Text #5

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.1645. Min Act: -0.0000

Data Index: 1508917 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.2823. Min Act: -0.0000

Data Index: 1456761 (The Pile)

Max Activating Token Index: 859

Text #7

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.3777. Min Act: -0.0000

Data Index: 436991 (The Pile)

Max Activating Token Index: 616

Text #8

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.2926. Min Act: -0.0000

Data Index: 1099563 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 3.7386. Min Range: -3.7386

Max Act: 2.9670. Min Act: -0.0000

Data Index: 985078 (The Pile)

Max Activating Token Index: 479

Text #10

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.2125. Min Act: -0.0000

Data Index: 1384672 (The Pile)

Max Activating Token Index: 805

Text #11

Max Range: 3.7386. Min Range: -3.7386

Max Act: 2.9167. Min Act: -0.0000

Data Index: 390460 (The Pile)

Max Activating Token Index: 697

Text #12

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.0163. Min Act: -0.0000

Data Index: 563633 (The Pile)

Max Activating Token Index: 919

Text #13

Max Range: 3.7386. Min Range: -3.7386

Max Act: 2.9177. Min Act: -0.0000

Data Index: 513055 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 3.7386. Min Range: -3.7386

Max Act: 2.9670. Min Act: -0.0000

Data Index: 1167850 (The Pile)

Max Activating Token Index: 984

Text #15

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.2318. Min Act: -0.0000

Data Index: 887911 (The Pile)

Max Activating Token Index: 150

Text #16

Max Range: 3.7386. Min Range: -3.7386

Max Act: 2.8958. Min Act: -0.0000

Data Index: 576677 (The Pile)

Max Activating Token Index: 965

Text #17

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.0519. Min Act: -0.0000

Data Index: 1419652 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 3.7386. Min Range: -3.7386

Max Act: 2.9218. Min Act: -0.0000

Data Index: 673749 (The Pile)

Max Activating Token Index: 1009

Text #19

Max Range: 3.7386. Min Range: -3.7386

Max Act: 2.8976. Min Act: -0.0000

Data Index: 1505666 (The Pile)

Max Activating Token Index: 127