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

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

Neuron 3877 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: 0.1284. Min Range: -0.1284

Max Act: 0.1275. Min Act: -0.0002

Data Index: 76095 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1284. Min Act: -0.0002

Data Index: 1308131 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1141. Min Act: -0.0002

Data Index: 236918 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0982. Min Act: -0.0002

Data Index: 1266415 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0865. Min Act: -0.0002

Data Index: 1209696 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0884. Min Act: -0.0001

Data Index: 688114 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0874. Min Act: -0.0002

Data Index: 459348 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0870. Min Act: -0.0002

Data Index: 1181150 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0872. Min Act: -0.0002

Data Index: 745993 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0747. Min Act: -0.0002

Data Index: 644784 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0884. Min Act: -0.0001

Data Index: 550230 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1306793 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0848. Min Act: -0.0001

Data Index: 976630 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0824. Min Act: -0.0002

Data Index: 272222 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0864. Min Act: -0.0002

Data Index: 1293768 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0832. Min Act: -0.0001

Data Index: 141499 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0827. Min Act: -0.0001

Data Index: 1102367 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0830. Min Act: -0.0002

Data Index: 348548 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0846. Min Act: -0.0001

Data Index: 178741 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0772. Min Act: -0.0002

Data Index: 170868 (C4 (Web Text))

Max Activating Token Index: 327