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

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

Neuron 243 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.8466. Min Act: -0.0000

Data Index: 529038 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.8180. Min Act: 0.0000

Data Index: 229958 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.5954. Min Act: -0.0000

Data Index: 129589 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.2596. Min Act: 0.0000

Data Index: 499219 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.3622. Min Act: -0.0000

Data Index: 662642 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.3728. Min Act: 0.0000

Data Index: 80282 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.4107. Min Act: -0.0000

Data Index: 93522 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.1021. Min Act: -0.0000

Data Index: 1116084 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.1790. Min Act: -0.0000

Data Index: 902336 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.1542. Min Act: -0.0000

Data Index: 1002397 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.1578. Min Act: -0.0000

Data Index: 102142 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.1420. Min Act: -0.0000

Data Index: 384359 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.1186. Min Act: -0.0000

Data Index: 661733 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.1003. Min Act: -0.0000

Data Index: 846820 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 2.8466. Min Range: -2.8466

Max Act: 1.9947. Min Act: -0.0000

Data Index: 1029790 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 2.8466. Min Range: -2.8466

Max Act: 1.9892. Min Act: -0.0000

Data Index: 408574 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.1832. Min Act: -0.0000

Data Index: 900895 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 2.8466. Min Range: -2.8466

Max Act: 1.9524. Min Act: -0.0000

Data Index: 353669 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.1511. Min Act: -0.0000

Data Index: 1186716 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 2.8466. Min Range: -2.8466

Max Act: 2.0576. Min Act: -0.0000

Data Index: 1240300 (C4 (Web Text))

Max Activating Token Index: 788