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

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

Neuron 820 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: 1.2073. Min Range: -1.2073

Max Act: 1.2073. Min Act: -0.0001

Data Index: 704728 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.1335. Min Act: -0.0001

Data Index: 15834 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.0049. Min Act: -0.0002

Data Index: 18828 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.1042. Min Act: -0.0001

Data Index: 393185 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.0887. Min Act: -0.0002

Data Index: 513333 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.0787. Min Act: -0.0001

Data Index: 349320 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.0414. Min Act: -0.0002

Data Index: 408324 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.0831. Min Act: -0.0001

Data Index: 792367 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 1.2073. Min Range: -1.2073

Max Act: 0.9764. Min Act: -0.0001

Data Index: 1164305 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.0038. Min Act: -0.0002

Data Index: 294880 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 1.2073. Min Range: -1.2073

Max Act: 0.9893. Min Act: -0.0001

Data Index: 1084913 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 1.2073. Min Range: -1.2073

Max Act: 0.9336. Min Act: -0.0001

Data Index: 710661 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 1.2073. Min Range: -1.2073

Max Act: 0.9851. Min Act: -0.0001

Data Index: 903465 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 1.2073. Min Range: -1.2073

Max Act: 0.9019. Min Act: -0.0001

Data Index: 1243288 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 1.2073. Min Range: -1.2073

Max Act: 1.0033. Min Act: -0.0001

Data Index: 745026 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 1.2073. Min Range: -1.2073

Max Act: 0.9623. Min Act: -0.0001

Data Index: 1343807 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 1.2073. Min Range: -1.2073

Max Act: 0.8283. Min Act: -0.0001

Data Index: 1058757 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 1.2073. Min Range: -1.2073

Max Act: 0.9932. Min Act: -0.0001

Data Index: 254974 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 1.2073. Min Range: -1.2073

Max Act: 0.9847. Min Act: -0.0001

Data Index: 1357283 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 1.2073. Min Range: -1.2073

Max Act: 0.9695. Min Act: -0.0001

Data Index: 315711 (C4 (Web Text))

Max Activating Token Index: 954