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

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

Neuron 3854 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1443. Min Act: -0.0002

Data Index: 278284 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1254. Min Act: -0.0002

Data Index: 1123585 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1228. Min Act: -0.0002

Data Index: 897826 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1217. Min Act: -0.0002

Data Index: 1031680 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1207. Min Act: -0.0002

Data Index: 7104 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1120. Min Act: -0.0002

Data Index: 815142 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1059. Min Act: -0.0002

Data Index: 1035777 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1114. Min Act: -0.0002

Data Index: 269452 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1039. Min Act: -0.0002

Data Index: 774653 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1026. Min Act: -0.0001

Data Index: 461409 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1002. Min Act: -0.0002

Data Index: 457851 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1004. Min Act: -0.0002

Data Index: 792327 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1226218 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.0885. Min Act: -0.0001

Data Index: 585287 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1338694 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.0898. Min Act: -0.0001

Data Index: 1158223 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.0922. Min Act: -0.0002

Data Index: 1183519 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.0931. Min Act: -0.0002

Data Index: 763931 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.0952. Min Act: -0.0002

Data Index: 485131 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.0979. Min Act: -0.0002

Data Index: 565107 (C4 (Web Text))

Max Activating Token Index: 937