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

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

Neuron 138 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.8922. Min Act: -0.0001

Data Index: 534598 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.5764. Min Act: -0.0001

Data Index: 405288 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.6827. Min Act: -0.0001

Data Index: 651890 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.5420. Min Act: -0.0001

Data Index: 634559 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.5278. Min Act: -0.0001

Data Index: 518362 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.5358. Min Act: -0.0001

Data Index: 309619 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.3647. Min Act: -0.0001

Data Index: 363716 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.6814. Min Act: -0.0001

Data Index: 195937 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.4570. Min Act: -0.0001

Data Index: 515280 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.5829. Min Act: -0.0001

Data Index: 760533 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.3495. Min Act: -0.0001

Data Index: 1145857 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.5224. Min Act: -0.0001

Data Index: 820312 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.4158. Min Act: -0.0001

Data Index: 1048598 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.2767. Min Act: -0.0001

Data Index: 205001 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.1276. Min Act: -0.0001

Data Index: 645370 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.2407. Min Act: -0.0001

Data Index: 714770 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.1935. Min Act: -0.0001

Data Index: 1262181 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.2060. Min Act: -0.0001

Data Index: 442186 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.3182. Min Act: -0.0001

Data Index: 604705 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.2927. Min Act: -0.0001

Data Index: 584632 (C4 (Web Text))

Max Activating Token Index: 884