Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 791 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 1.1638. Min Range: -1.1638

Max Act: 1.1638. Min Act: -0.0003

Data Index: 817498 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 1.1638. Min Range: -1.1638

Max Act: 1.0217. Min Act: -0.0003

Data Index: 434240 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.9571. Min Act: -0.0003

Data Index: 821561 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.9241. Min Act: -0.0003

Data Index: 281837 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.9018. Min Act: -0.0003

Data Index: 613564 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.8296. Min Act: -0.0003

Data Index: 1032365 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.8721. Min Act: -0.0003

Data Index: 569355 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.8502. Min Act: -0.0003

Data Index: 667258 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.8354. Min Act: -0.0003

Data Index: 956763 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.7847. Min Act: -0.0003

Data Index: 846369 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.7224. Min Act: -0.0003

Data Index: 904431 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.7074. Min Act: -0.0003

Data Index: 493172 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.7262. Min Act: -0.0003

Data Index: 381738 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.7603. Min Act: -0.0003

Data Index: 1325252 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.7383. Min Act: -0.0003

Data Index: 837069 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.7419. Min Act: -0.0003

Data Index: 32874 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.7250. Min Act: -0.0003

Data Index: 890878 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.7167. Min Act: -0.0003

Data Index: 237603 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.7138. Min Act: -0.0003

Data Index: 754577 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.6943. Min Act: -0.0003

Data Index: 631344 (C4 (Web Text))

Max Activating Token Index: 213