Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1416 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.6769. Min Act: -0.0000

Data Index: 829630 (The Pile)

Max Activating Token Index: 424

Text #1

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.6759. Min Act: -0.0000

Data Index: 317383 (The Pile)

Max Activating Token Index: 787

Text #2

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1651246 (The Pile)

Max Activating Token Index: 553

Text #3

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.6187. Min Act: -0.0000

Data Index: 223075 (The Pile)

Max Activating Token Index: 762

Text #4

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.5513. Min Act: -0.0000

Data Index: 851371 (The Pile)

Max Activating Token Index: 31

Text #5

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1138939 (The Pile)

Max Activating Token Index: 101

Text #6

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.5111. Min Act: -0.0000

Data Index: 851378 (The Pile)

Max Activating Token Index: 176

Text #7

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1645834 (The Pile)

Max Activating Token Index: 307

Text #8

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.5186. Min Act: 0.0000

Data Index: 224674 (The Pile)

Max Activating Token Index: 59

Text #9

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1804385 (The Pile)

Max Activating Token Index: 126

Text #10

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.4968. Min Act: -0.0000

Data Index: 1306031 (The Pile)

Max Activating Token Index: 483

Text #11

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.4842. Min Act: -0.0000

Data Index: 5145 (The Pile)

Max Activating Token Index: 98

Text #12

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1816990 (The Pile)

Max Activating Token Index: 991

Text #13

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.4666. Min Act: -0.0000

Data Index: 1877748 (The Pile)

Max Activating Token Index: 929

Text #14

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.4451. Min Act: -0.0000

Data Index: 811574 (The Pile)

Max Activating Token Index: 1005

Text #15

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1388624 (The Pile)

Max Activating Token Index: 927

Text #16

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.4471. Min Act: -0.0000

Data Index: 839763 (The Pile)

Max Activating Token Index: 834

Text #17

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.4421. Min Act: -0.0000

Data Index: 1456471 (The Pile)

Max Activating Token Index: 540

Text #18

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.4404. Min Act: -0.0000

Data Index: 421429 (The Pile)

Max Activating Token Index: 920

Text #19

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1683055 (The Pile)

Max Activating Token Index: 714