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

Dataset: The Pile

Neuron 65 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: 1.8409. Min Range: -1.8409

Max Act: 1.8409. Min Act: -0.0000

Data Index: 623848 (The Pile)

Max Activating Token Index: 863

Text #1

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.5330. Min Act: -0.0000

Data Index: 80769 (The Pile)

Max Activating Token Index: 480

Text #2

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.4049. Min Act: -0.0000

Data Index: 1695415 (The Pile)

Max Activating Token Index: 712

Text #3

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.3289. Min Act: -0.0000

Data Index: 780571 (The Pile)

Max Activating Token Index: 172

Text #4

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.4789. Min Act: -0.0000

Data Index: 732736 (The Pile)

Max Activating Token Index: 690

Text #5

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.3626. Min Act: -0.0000

Data Index: 1421559 (The Pile)

Max Activating Token Index: 369

Text #6

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.3638. Min Act: -0.0000

Data Index: 1599959 (The Pile)

Max Activating Token Index: 583

Text #7

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.3521. Min Act: -0.0000

Data Index: 14471 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.3393. Min Act: -0.0000

Data Index: 1398719 (The Pile)

Max Activating Token Index: 721

Text #9

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.2045. Min Act: -0.0000

Data Index: 1469148 (The Pile)

Max Activating Token Index: 812

Text #10

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.2902. Min Act: -0.0000

Data Index: 341921 (The Pile)

Max Activating Token Index: 815

Text #11

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.2762. Min Act: -0.0000

Data Index: 1907915 (The Pile)

Max Activating Token Index: 478

Text #12

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.2249. Min Act: -0.0000

Data Index: 1578942 (The Pile)

Max Activating Token Index: 141

Text #13

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.2540. Min Act: -0.0000

Data Index: 716787 (The Pile)

Max Activating Token Index: 712

Text #14

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.3126. Min Act: -0.0000

Data Index: 103074 (The Pile)

Max Activating Token Index: 623

Text #15

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.1699. Min Act: -0.0000

Data Index: 1270330 (The Pile)

Max Activating Token Index: 954

Text #16

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.1238. Min Act: -0.0000

Data Index: 842680 (The Pile)

Max Activating Token Index: 130

Text #17

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.1917. Min Act: -0.0000

Data Index: 438149 (The Pile)

Max Activating Token Index: 855

Text #18

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.0159. Min Act: -0.0000

Data Index: 786547 (The Pile)

Max Activating Token Index: 862

Text #19

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.2013. Min Act: -0.0000

Data Index: 188738 (The Pile)

Max Activating Token Index: 869