Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 996 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.1492. Min Range: -7.1492

Max Act: 7.1492. Min Act: -0.0000

Data Index: 969321 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 7.1492. Min Range: -7.1492

Max Act: 6.3648. Min Act: -0.0000

Data Index: 1276739 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 7.1492. Min Range: -7.1492

Max Act: 5.9297. Min Act: -0.0000

Data Index: 158062 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 7.1492. Min Range: -7.1492

Max Act: 6.1351. Min Act: -0.0000

Data Index: 280773 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 7.1492. Min Range: -7.1492

Max Act: 5.9951. Min Act: -0.0000

Data Index: 476079 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 7.1492. Min Range: -7.1492

Max Act: 5.6155. Min Act: -0.0000

Data Index: 447575 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 7.1492. Min Range: -7.1492

Max Act: 5.5527. Min Act: -0.0000

Data Index: 1259247 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 7.1492. Min Range: -7.1492

Max Act: 5.3281. Min Act: -0.0000

Data Index: 319667 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 7.1492. Min Range: -7.1492

Max Act: 5.5652. Min Act: -0.0000

Data Index: 740343 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 7.1492. Min Range: -7.1492

Max Act: 5.8174. Min Act: -0.0000

Data Index: 802299 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 7.1492. Min Range: -7.1492

Max Act: 5.1248. Min Act: -0.0000

Data Index: 157240 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 7.1492. Min Range: -7.1492

Max Act: 5.2917. Min Act: -0.0000

Data Index: 1162910 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 7.1492. Min Range: -7.1492

Max Act: 5.4922. Min Act: -0.0000

Data Index: 601445 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 7.1492. Min Range: -7.1492

Max Act: 4.9683. Min Act: -0.0000

Data Index: 350580 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 7.1492. Min Range: -7.1492

Max Act: 5.0858. Min Act: -0.0000

Data Index: 157238 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 7.1492. Min Range: -7.1492

Max Act: 5.2041. Min Act: -0.0000

Data Index: 140718 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 7.1492. Min Range: -7.1492

Max Act: 5.2388. Min Act: -0.0000

Data Index: 905428 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 7.1492. Min Range: -7.1492

Max Act: 5.1724. Min Act: -0.0000

Data Index: 1228663 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 7.1492. Min Range: -7.1492

Max Act: 5.3667. Min Act: -0.0000

Data Index: 651631 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 7.1492. Min Range: -7.1492

Max Act: 5.3250. Min Act: -0.0000

Data Index: 442527 (C4 (Web Text))

Max Activating Token Index: 257