Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 360 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.3447. Min Act: -0.0001

Data Index: 785587 (The Pile)

Max Activating Token Index: 925

Text #1

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2631. Min Act: -0.0000

Data Index: 102236 (The Pile)

Max Activating Token Index: 196

Text #2

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1351823 (The Pile)

Max Activating Token Index: 778

Text #3

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1238886 (The Pile)

Max Activating Token Index: 376

Text #4

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2947. Min Act: -0.0000

Data Index: 1452538 (The Pile)

Max Activating Token Index: 765

Text #5

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.3049. Min Act: -0.0000

Data Index: 1038816 (The Pile)

Max Activating Token Index: 390

Text #6

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2935. Min Act: -0.0000

Data Index: 52941 (The Pile)

Max Activating Token Index: 80

Text #7

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2944. Min Act: -0.0000

Data Index: 561349 (The Pile)

Max Activating Token Index: 838

Text #8

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1747435 (The Pile)

Max Activating Token Index: 349

Text #9

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2687. Min Act: -0.0000

Data Index: 28434 (The Pile)

Max Activating Token Index: 57

Text #10

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1300902 (The Pile)

Max Activating Token Index: 542

Text #11

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.1955. Min Act: -0.0000

Data Index: 1140932 (The Pile)

Max Activating Token Index: 154

Text #12

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2622. Min Act: -0.0000

Data Index: 982524 (The Pile)

Max Activating Token Index: 524

Text #13

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2174. Min Act: -0.0001

Data Index: 4302 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1968347 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1736191 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2466. Min Act: -0.0000

Data Index: 1474633 (The Pile)

Max Activating Token Index: 152

Text #17

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1353765 (The Pile)

Max Activating Token Index: 468

Text #18

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1804956 (The Pile)

Max Activating Token Index: 493

Text #19

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1073165 (The Pile)

Max Activating Token Index: 191