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

Dataset: The Pile

Neuron 257 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.3290. Min Act: -0.0000

Data Index: 290697 (The Pile)

Max Activating Token Index: 978

Text #1

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.3174. Min Act: -0.0000

Data Index: 929983 (The Pile)

Max Activating Token Index: 249

Text #2

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.3255. Min Act: -0.0000

Data Index: 1390803 (The Pile)

Max Activating Token Index: 648

Text #3

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.3179. Min Act: -0.0000

Data Index: 1127679 (The Pile)

Max Activating Token Index: 952

Text #4

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.3045. Min Act: -0.0000

Data Index: 880086 (The Pile)

Max Activating Token Index: 682

Text #5

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.3017. Min Act: -0.0000

Data Index: 1310111 (The Pile)

Max Activating Token Index: 59

Text #6

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.3063. Min Act: -0.0000

Data Index: 1809895 (The Pile)

Max Activating Token Index: 461

Text #7

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2950. Min Act: 0.0000

Data Index: 1434801 (The Pile)

Max Activating Token Index: 378

Text #8

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2958. Min Act: 0.0000

Data Index: 1337223 (The Pile)

Max Activating Token Index: 851

Text #9

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2892. Min Act: -0.0000

Data Index: 867875 (The Pile)

Max Activating Token Index: 623

Text #10

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2998. Min Act: -0.0000

Data Index: 120770 (The Pile)

Max Activating Token Index: 639

Text #11

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.3066. Min Act: -0.0000

Data Index: 823372 (The Pile)

Max Activating Token Index: 951

Text #12

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2947. Min Act: 0.0000

Data Index: 117222 (The Pile)

Max Activating Token Index: 255

Text #13

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2761. Min Act: -0.0000

Data Index: 1772020 (The Pile)

Max Activating Token Index: 957

Text #14

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2699. Min Act: -0.0000

Data Index: 274856 (The Pile)

Max Activating Token Index: 606

Text #15

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2837. Min Act: 0.0000

Data Index: 961439 (The Pile)

Max Activating Token Index: 872

Text #16

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2725. Min Act: 0.0000

Data Index: 1887019 (The Pile)

Max Activating Token Index: 200

Text #17

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2663. Min Act: -0.0000

Data Index: 895568 (The Pile)

Max Activating Token Index: 792

Text #18

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1568565 (The Pile)

Max Activating Token Index: 689

Text #19

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2744. Min Act: 0.0000

Data Index: 1032325 (The Pile)

Max Activating Token Index: 205