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

Dataset: The Pile

Neuron 1997 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: 0.1208. Min Range: -0.1208

Max Act: 0.1208. Min Act: -0.0000

Data Index: 1287928 (The Pile)

Max Activating Token Index: 460

Text #1

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0954. Min Act: 0.0000

Data Index: 275912 (The Pile)

Max Activating Token Index: 836

Text #2

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0976. Min Act: -0.0000

Data Index: 194730 (The Pile)

Max Activating Token Index: 908

Text #3

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1003. Min Act: -0.0000

Data Index: 605408 (The Pile)

Max Activating Token Index: 1017

Text #4

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0970. Min Act: -0.0000

Data Index: 1757558 (The Pile)

Max Activating Token Index: 751

Text #5

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1388406 (The Pile)

Max Activating Token Index: 394

Text #6

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0914. Min Act: -0.0000

Data Index: 1455937 (The Pile)

Max Activating Token Index: 117

Text #7

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0821. Min Act: -0.0000

Data Index: 195042 (The Pile)

Max Activating Token Index: 741

Text #8

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0826. Min Act: -0.0000

Data Index: 1804042 (The Pile)

Max Activating Token Index: 451

Text #9

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0793. Min Act: -0.0000

Data Index: 305684 (The Pile)

Max Activating Token Index: 310

Text #10

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1905905 (The Pile)

Max Activating Token Index: 962

Text #11

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0814. Min Act: -0.0000

Data Index: 242449 (The Pile)

Max Activating Token Index: 406

Text #12

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0828. Min Act: 0.0001

Data Index: 291270 (The Pile)

Max Activating Token Index: 675

Text #13

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0793. Min Act: 0.0001

Data Index: 997959 (The Pile)

Max Activating Token Index: 861

Text #14

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0737. Min Act: -0.0000

Data Index: 1297906 (The Pile)

Max Activating Token Index: 1007

Text #15

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0785. Min Act: -0.0000

Data Index: 699531 (The Pile)

Max Activating Token Index: 41

Text #16

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0789. Min Act: -0.0000

Data Index: 733464 (The Pile)

Max Activating Token Index: 590

Text #17

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0787. Min Act: -0.0000

Data Index: 1364130 (The Pile)

Max Activating Token Index: 813

Text #18

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0825. Min Act: -0.0000

Data Index: 1759827 (The Pile)

Max Activating Token Index: 612

Text #19

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0774. Min Act: 0.0003

Data Index: 238911 (The Pile)

Max Activating Token Index: 300