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

Dataset: The Pile

Neuron 1459 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.9862. Min Act: -0.0000

Data Index: 1625559 (The Pile)

Max Activating Token Index: 641

Text #1

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.8344. Min Act: 0.0000

Data Index: 548639 (The Pile)

Max Activating Token Index: 624

Text #2

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.9073. Min Act: -0.0000

Data Index: 1075369 (The Pile)

Max Activating Token Index: 514

Text #3

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.7899. Min Act: -0.0000

Data Index: 719957 (The Pile)

Max Activating Token Index: 857

Text #4

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.8304. Min Act: -0.0000

Data Index: 947827 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.7720. Min Act: -0.0000

Data Index: 1719456 (The Pile)

Max Activating Token Index: 445

Text #6

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1190613 (The Pile)

Max Activating Token Index: 835

Text #7

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.7287. Min Act: -0.0000

Data Index: 1605276 (The Pile)

Max Activating Token Index: 651

Text #8

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.6734. Min Act: -0.0000

Data Index: 911121 (The Pile)

Max Activating Token Index: 774

Text #9

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.7327. Min Act: -0.0000

Data Index: 1035388 (The Pile)

Max Activating Token Index: 546

Text #10

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.7899. Min Act: -0.0000

Data Index: 1366311 (The Pile)

Max Activating Token Index: 775

Text #11

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.7086. Min Act: -0.0000

Data Index: 107002 (The Pile)

Max Activating Token Index: 644

Text #12

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1644533 (The Pile)

Max Activating Token Index: 903

Text #13

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.6438. Min Act: -0.0000

Data Index: 506970 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.6550. Min Act: -0.0000

Data Index: 1159628 (The Pile)

Max Activating Token Index: 787

Text #15

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.6092. Min Act: -0.0000

Data Index: 1514876 (The Pile)

Max Activating Token Index: 891

Text #16

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.6929. Min Act: -0.0000

Data Index: 413777 (The Pile)

Max Activating Token Index: 512

Text #17

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1580802 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1882063 (The Pile)

Max Activating Token Index: 91

Text #19

Max Range: 0.9862. Min Range: -0.9862

Max Act: 0.6465. Min Act: -0.0000

Data Index: 270723 (The Pile)

Max Activating Token Index: 173