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

Dataset: The Pile

Neuron 3047 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.3671. Min Act: -0.0000

Data Index: 1852721 (The Pile)

Max Activating Token Index: 891

Text #1

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.2222. Min Act: -0.0000

Data Index: 1272440 (The Pile)

Max Activating Token Index: 769

Text #2

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.0801. Min Act: -0.0000

Data Index: 744763 (The Pile)

Max Activating Token Index: 516

Text #3

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.9410. Min Act: -0.0000

Data Index: 207037 (The Pile)

Max Activating Token Index: 106

Text #4

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.0168. Min Act: -0.0000

Data Index: 1775802 (The Pile)

Max Activating Token Index: 130

Text #5

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1376957 (The Pile)

Max Activating Token Index: 1001

Text #6

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.9482. Min Act: -0.0000

Data Index: 1976195 (The Pile)

Max Activating Token Index: 351

Text #7

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.8868. Min Act: -0.0000

Data Index: 126926 (The Pile)

Max Activating Token Index: 827

Text #8

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1190947 (The Pile)

Max Activating Token Index: 46

Text #9

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.8337. Min Act: -0.0000

Data Index: 1397620 (The Pile)

Max Activating Token Index: 303

Text #10

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.8480. Min Act: -0.0000

Data Index: 859625 (The Pile)

Max Activating Token Index: 298

Text #11

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.9165. Min Act: -0.0000

Data Index: 1521324 (The Pile)

Max Activating Token Index: 54

Text #12

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.7688. Min Act: -0.0000

Data Index: 194931 (The Pile)

Max Activating Token Index: 564

Text #13

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.8512. Min Act: -0.0000

Data Index: 1346443 (The Pile)

Max Activating Token Index: 1007

Text #14

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1721200 (The Pile)

Max Activating Token Index: 588

Text #15

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1297586 (The Pile)

Max Activating Token Index: 315

Text #16

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.7434. Min Act: -0.0000

Data Index: 349602 (The Pile)

Max Activating Token Index: 918

Text #17

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.8551. Min Act: -0.0000

Data Index: 252457 (The Pile)

Max Activating Token Index: 65

Text #18

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.7791. Min Act: -0.0000

Data Index: 133104 (The Pile)

Max Activating Token Index: 332

Text #19

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1462464 (The Pile)

Max Activating Token Index: 213