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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1321 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2497. Min Act: -0.0000

Data Index: 851603 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1598336 (Python Code)

Max Activating Token Index: 233

Text #2

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2268. Min Act: -0.0000

Data Index: 1333229 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1081146 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1397277 (Python Code)

Max Activating Token Index: 650

Text #5

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1550658 (Python Code)

Max Activating Token Index: 552

Text #6

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2046. Min Act: -0.0001

Data Index: 647353 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1959. Min Act: -0.0001

Data Index: 1482466 (Python Code)

Max Activating Token Index: 342

Text #8

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1986. Min Act: -0.0001

Data Index: 803416 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1909. Min Act: -0.0000

Data Index: 272155 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1959. Min Act: -0.0000

Data Index: 996354 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1924. Min Act: -0.0001

Data Index: 812613 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1891. Min Act: -0.0000

Data Index: 1440416 (Python Code)

Max Activating Token Index: 208

Text #13

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1894. Min Act: -0.0000

Data Index: 823806 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1555981 (Python Code)

Max Activating Token Index: 524

Text #15

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1802. Min Act: -0.0000

Data Index: 447916 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1776. Min Act: -0.0000

Data Index: 1316076 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1760. Min Act: -0.0001

Data Index: 1084969 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1734. Min Act: -0.0000

Data Index: 983581 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1758. Min Act: -0.0001

Data Index: 1163818 (C4 (Web Text))

Max Activating Token Index: 632