Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 388 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.2371. Min Range: -1.2371

Max Act: 1.2371. Min Act: -0.0004

Data Index: 581476 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 1.2371. Min Range: -1.2371

Max Act: 1.1695. Min Act: -0.0004

Data Index: 99422 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 1.2371. Min Range: -1.2371

Max Act: 1.1668. Min Act: -0.0004

Data Index: 176424 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 1.2371. Min Range: -1.2371

Max Act: 1.0586. Min Act: -0.0004

Data Index: 156545 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 1.2371. Min Range: -1.2371

Max Act: 1.0321. Min Act: -0.0004

Data Index: 310106 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 1.2371. Min Range: -1.2371

Max Act: 1.0116. Min Act: -0.0004

Data Index: 806268 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.9691. Min Act: -0.0004

Data Index: 117053 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.9308. Min Act: -0.0004

Data Index: 335117 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.9791. Min Act: -0.0004

Data Index: 503735 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.9813. Min Act: -0.0004

Data Index: 887627 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 1.2371. Min Range: -1.2371

Max Act: 1.0345. Min Act: -0.0004

Data Index: 742140 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 1.2371. Min Range: -1.2371

Max Act: 1.0129. Min Act: -0.0004

Data Index: 505821 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.9097. Min Act: -0.0004

Data Index: 697744 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.8633. Min Act: -0.0004

Data Index: 1218391 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.9693. Min Act: -0.0004

Data Index: 310447 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.8891. Min Act: -0.0004

Data Index: 393982 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.9574. Min Act: -0.0004

Data Index: 1174208 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.9124. Min Act: -0.0004

Data Index: 652437 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.8999. Min Act: -0.0004

Data Index: 458628 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 1.2371. Min Range: -1.2371

Max Act: 0.8914. Min Act: -0.0004

Data Index: 1262242 (C4 (Web Text))

Max Activating Token Index: 494