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

Dataset: The Pile

Neuron 3227 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1131. Min Act: -0.0000

Data Index: 839735 (The Pile)

Max Activating Token Index: 1022

Text #1

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1492214 (The Pile)

Max Activating Token Index: 469

Text #2

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0981. Min Act: -0.0000

Data Index: 1621850 (The Pile)

Max Activating Token Index: 645

Text #3

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0920. Min Act: -0.0000

Data Index: 65881 (The Pile)

Max Activating Token Index: 655

Text #4

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0932. Min Act: -0.0000

Data Index: 854843 (The Pile)

Max Activating Token Index: 83

Text #5

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0931. Min Act: -0.0000

Data Index: 1955760 (The Pile)

Max Activating Token Index: 900

Text #6

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0924. Min Act: -0.0000

Data Index: 920514 (The Pile)

Max Activating Token Index: 130

Text #7

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0885. Min Act: -0.0000

Data Index: 1358161 (The Pile)

Max Activating Token Index: 903

Text #8

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0884. Min Act: -0.0000

Data Index: 197637 (The Pile)

Max Activating Token Index: 529

Text #9

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0887. Min Act: -0.0000

Data Index: 82588 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1069776 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0896. Min Act: -0.0000

Data Index: 322464 (The Pile)

Max Activating Token Index: 829

Text #12

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0842. Min Act: -0.0000

Data Index: 697344 (The Pile)

Max Activating Token Index: 19

Text #13

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0856. Min Act: -0.0000

Data Index: 79421 (The Pile)

Max Activating Token Index: 849

Text #14

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0878. Min Act: 0.0000

Data Index: 1443083 (The Pile)

Max Activating Token Index: 770

Text #15

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0851. Min Act: -0.0000

Data Index: 1565445 (The Pile)

Max Activating Token Index: 200

Text #16

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0873. Min Act: -0.0000

Data Index: 1983961 (The Pile)

Max Activating Token Index: 170

Text #17

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0805. Min Act: -0.0000

Data Index: 970117 (The Pile)

Max Activating Token Index: 744

Text #18

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0805. Min Act: -0.0000

Data Index: 50254 (The Pile)

Max Activating Token Index: 280

Text #19

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1719114 (The Pile)

Max Activating Token Index: 679