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

Dataset: The Pile

Neuron 4893 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.4464. Min Act: -0.0000

Data Index: 314818 (The Pile)

Max Activating Token Index: 461

Text #1

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.3914. Min Act: -0.0000

Data Index: 33221 (The Pile)

Max Activating Token Index: 232

Text #2

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.2451. Min Act: -0.0000

Data Index: 37318 (The Pile)

Max Activating Token Index: 516

Text #3

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.2099. Min Act: -0.0000

Data Index: 353454 (The Pile)

Max Activating Token Index: 967

Text #4

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.1170. Min Act: -0.0000

Data Index: 1945683 (The Pile)

Max Activating Token Index: 728

Text #5

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.0891. Min Act: -0.0000

Data Index: 647320 (The Pile)

Max Activating Token Index: 684

Text #6

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.1512. Min Act: -0.0000

Data Index: 1355963 (The Pile)

Max Activating Token Index: 566

Text #7

Max Range: 1.4464. Min Range: -1.4464

Max Act: 0.9432. Min Act: -0.0000

Data Index: 1843489 (The Pile)

Max Activating Token Index: 870

Text #8

Max Range: 1.4464. Min Range: -1.4464

Max Act: 0.9132. Min Act: -0.0000

Data Index: 524225 (The Pile)

Max Activating Token Index: 253

Text #9

Max Range: 1.4464. Min Range: -1.4464

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1523827 (The Pile)

Max Activating Token Index: 843

Text #10

Max Range: 1.4464. Min Range: -1.4464

Max Act: 1.0522. Min Act: -0.0000

Data Index: 299944 (The Pile)

Max Activating Token Index: 525

Text #11

Max Range: 1.4464. Min Range: -1.4464

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1374793 (The Pile)

Max Activating Token Index: 682

Text #12

Max Range: 1.4464. Min Range: -1.4464

Max Act: 0.9881. Min Act: -0.0000

Data Index: 1095762 (The Pile)

Max Activating Token Index: 902

Text #13

Max Range: 1.4464. Min Range: -1.4464

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1311244 (The Pile)

Max Activating Token Index: 333

Text #14

Max Range: 1.4464. Min Range: -1.4464

Max Act: 0.8881. Min Act: -0.0000

Data Index: 52576 (The Pile)

Max Activating Token Index: 781

Text #15

Max Range: 1.4464. Min Range: -1.4464

Max Act: 0.8936. Min Act: -0.0000

Data Index: 38032 (The Pile)

Max Activating Token Index: 147

Text #16

Max Range: 1.4464. Min Range: -1.4464

Max Act: 0.8960. Min Act: -0.0000

Data Index: 349776 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 1.4464. Min Range: -1.4464

Max Act: 0.9047. Min Act: -0.0000

Data Index: 1036657 (The Pile)

Max Activating Token Index: 477

Text #18

Max Range: 1.4464. Min Range: -1.4464

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1476568 (The Pile)

Max Activating Token Index: 101

Text #19

Max Range: 1.4464. Min Range: -1.4464

Max Act: 0.8304. Min Act: -0.0000

Data Index: 1592834 (The Pile)

Max Activating Token Index: 425