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

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

Neuron 2911 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6985. Min Range: -2.6985

Max Act: 2.6985. Min Act: -0.0000

Data Index: 129714 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 2.6985. Min Range: -2.6985

Max Act: 2.2039. Min Act: -0.0000

Data Index: 260434 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 2.6985. Min Range: -2.6985

Max Act: 2.0673. Min Act: -0.0000

Data Index: 1270000 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 2.6985. Min Range: -2.6985

Max Act: 2.0645. Min Act: -0.0000

Data Index: 40613 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.9519. Min Act: -0.0000

Data Index: 113701 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.9437. Min Act: -0.0000

Data Index: 1357972 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.9386. Min Act: -0.0000

Data Index: 662856 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.9229. Min Act: -0.0000

Data Index: 361028 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.9214. Min Act: -0.0000

Data Index: 1179864 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.8913. Min Act: -0.0000

Data Index: 559808 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.8489. Min Act: -0.0001

Data Index: 680092 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.8476. Min Act: -0.0000

Data Index: 641918 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.8390. Min Act: -0.0000

Data Index: 1036904 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.8376. Min Act: -0.0000

Data Index: 766828 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.8395. Min Act: -0.0001

Data Index: 1093230 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.7306. Min Act: -0.0000

Data Index: 460003 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.7836. Min Act: -0.0000

Data Index: 850835 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.7490. Min Act: -0.0000

Data Index: 869843 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.7555. Min Act: -0.0000

Data Index: 1281566 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.7549. Min Act: -0.0000

Data Index: 299574 (C4 (Web Text))

Max Activating Token Index: 714