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

Dataset: The Pile

Neuron 2074 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: 3.8945. Min Range: -3.8945

Max Act: 3.8945. Min Act: -0.0000

Data Index: 1336648 (The Pile)

Max Activating Token Index: 990

Text #1

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.6256. Min Act: -0.0000

Data Index: 193490 (The Pile)

Max Activating Token Index: 941

Text #2

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.6533. Min Act: -0.0000

Data Index: 1598630 (The Pile)

Max Activating Token Index: 938

Text #3

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.5496. Min Act: -0.0000

Data Index: 361996 (The Pile)

Max Activating Token Index: 1019

Text #4

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.2495. Min Act: -0.0000

Data Index: 483120 (The Pile)

Max Activating Token Index: 59

Text #5

Max Range: 3.8945. Min Range: -3.8945

Max Act: 2.9461. Min Act: -0.0000

Data Index: 386388 (The Pile)

Max Activating Token Index: 990

Text #6

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.0184. Min Act: -0.0000

Data Index: 1546465 (The Pile)

Max Activating Token Index: 404

Text #7

Max Range: 3.8945. Min Range: -3.8945

Max Act: 2.6981. Min Act: -0.0000

Data Index: 856223 (The Pile)

Max Activating Token Index: 768

Text #8

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.2727. Min Act: -0.0000

Data Index: 939012 (The Pile)

Max Activating Token Index: 964

Text #9

Max Range: 3.8945. Min Range: -3.8945

Max Act: 2.4549. Min Act: -0.0000

Data Index: 1176299 (The Pile)

Max Activating Token Index: 902

Text #10

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.0251. Min Act: -0.0000

Data Index: 904276 (The Pile)

Max Activating Token Index: 172

Text #11

Max Range: 3.8945. Min Range: -3.8945

Max Act: 2.7172. Min Act: -0.0000

Data Index: 451346 (The Pile)

Max Activating Token Index: 995

Text #12

Max Range: 3.8945. Min Range: -3.8945

Max Act: 2.6071. Min Act: -0.0000

Data Index: 103974 (The Pile)

Max Activating Token Index: 772

Text #13

Max Range: 3.8945. Min Range: -3.8945

Max Act: 2.7853. Min Act: -0.0000

Data Index: 700752 (The Pile)

Max Activating Token Index: 963

Text #14

Max Range: 3.8945. Min Range: -3.8945

Max Act: 2.9178. Min Act: -0.0000

Data Index: 298423 (The Pile)

Max Activating Token Index: 789

Text #15

Max Range: 3.8945. Min Range: -3.8945

Max Act: 2.4283. Min Act: -0.0000

Data Index: 1941163 (The Pile)

Max Activating Token Index: 501

Text #16

Max Range: 3.8945. Min Range: -3.8945

Max Act: 2.8284. Min Act: -0.0000

Data Index: 1474729 (The Pile)

Max Activating Token Index: 655

Text #17

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.4434. Min Act: -0.0000

Data Index: 712830 (The Pile)

Max Activating Token Index: 821

Text #18

Max Range: 3.8945. Min Range: -3.8945

Max Act: 2.6950. Min Act: -0.0000

Data Index: 907422 (The Pile)

Max Activating Token Index: 719

Text #19

Max Range: 3.8945. Min Range: -3.8945

Max Act: 2.0529. Min Act: -0.0000

Data Index: 21481 (The Pile)

Max Activating Token Index: 680