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

Dataset: The Pile

Neuron 2087 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2515. Min Range: -1.2515

Max Act: 1.2515. Min Act: -0.0000

Data Index: 1903234 (The Pile)

Max Activating Token Index: 47

Text #1

Max Range: 1.2515. Min Range: -1.2515

Max Act: 1.1402. Min Act: -0.0000

Data Index: 1772116 (The Pile)

Max Activating Token Index: 846

Text #2

Max Range: 1.2515. Min Range: -1.2515

Max Act: 1.0819. Min Act: -0.0000

Data Index: 1353330 (The Pile)

Max Activating Token Index: 983

Text #3

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8952. Min Act: -0.0000

Data Index: 1934048 (The Pile)

Max Activating Token Index: 567

Text #4

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.9830. Min Act: -0.0000

Data Index: 1296476 (The Pile)

Max Activating Token Index: 943

Text #5

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8716. Min Act: -0.0000

Data Index: 501912 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8971. Min Act: -0.0000

Data Index: 917043 (The Pile)

Max Activating Token Index: 945

Text #7

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.9849. Min Act: -0.0000

Data Index: 1256423 (The Pile)

Max Activating Token Index: 785

Text #8

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.9915. Min Act: -0.0000

Data Index: 1965581 (The Pile)

Max Activating Token Index: 811

Text #9

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.9548. Min Act: -0.0000

Data Index: 1265482 (The Pile)

Max Activating Token Index: 975

Text #10

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.9463. Min Act: -0.0000

Data Index: 1290881 (The Pile)

Max Activating Token Index: 936

Text #11

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8493. Min Act: -0.0000

Data Index: 878689 (The Pile)

Max Activating Token Index: 1006

Text #12

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1363739 (The Pile)

Max Activating Token Index: 281

Text #13

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.9220. Min Act: -0.0000

Data Index: 752887 (The Pile)

Max Activating Token Index: 874

Text #14

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.9172. Min Act: -0.0000

Data Index: 832339 (The Pile)

Max Activating Token Index: 561

Text #15

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.9068. Min Act: -0.0000

Data Index: 1687120 (The Pile)

Max Activating Token Index: 413

Text #16

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.8520. Min Act: -0.0000

Data Index: 853285 (The Pile)

Max Activating Token Index: 667

Text #17

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.9112. Min Act: -0.0000

Data Index: 677362 (The Pile)

Max Activating Token Index: 301

Text #18

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.9276. Min Act: -0.0000

Data Index: 579412 (The Pile)

Max Activating Token Index: 762

Text #19

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.9332. Min Act: -0.0000

Data Index: 1423013 (The Pile)

Max Activating Token Index: 725