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

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

Neuron 3816 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1180. Min Act: -0.0002

Data Index: 303839 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1163. Min Act: -0.0002

Data Index: 1285064 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1157. Min Act: -0.0002

Data Index: 1108315 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1159. Min Act: -0.0002

Data Index: 615607 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1104. Min Act: -0.0002

Data Index: 1292780 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1088. Min Act: -0.0002

Data Index: 209266 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0922. Min Act: -0.0002

Data Index: 25260 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0889. Min Act: -0.0002

Data Index: 866524 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0905. Min Act: -0.0002

Data Index: 234601 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0932. Min Act: -0.0002

Data Index: 507671 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0903. Min Act: -0.0002

Data Index: 336824 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0940. Min Act: -0.0002

Data Index: 478530 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1145149 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0970. Min Act: -0.0002

Data Index: 1208556 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0885. Min Act: -0.0002

Data Index: 132746 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0880. Min Act: -0.0002

Data Index: 181789 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0903. Min Act: -0.0002

Data Index: 973721 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1204649 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0775. Min Act: -0.0002

Data Index: 869555 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0825. Min Act: -0.0002

Data Index: 139602 (C4 (Web Text))

Max Activating Token Index: 233