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

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

Neuron 4835 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3941. Min Range: -1.3941

Max Act: 1.3941. Min Act: -0.0000

Data Index: 1213454 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 1.3941. Min Range: -1.3941

Max Act: 1.2769. Min Act: -0.0000

Data Index: 230880 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 1.3941. Min Range: -1.3941

Max Act: 1.0376. Min Act: -0.0000

Data Index: 113912 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 1.3941. Min Range: -1.3941

Max Act: 1.0648. Min Act: -0.0000

Data Index: 311168 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 1.3941. Min Range: -1.3941

Max Act: 0.9331. Min Act: -0.0000

Data Index: 1095591 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 1.3941. Min Range: -1.3941

Max Act: 0.9733. Min Act: -0.0000

Data Index: 776885 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 1.3941. Min Range: -1.3941

Max Act: 0.9118. Min Act: -0.0000

Data Index: 839080 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 1.3941. Min Range: -1.3941

Max Act: 0.8324. Min Act: -0.0000

Data Index: 753747 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 1.3941. Min Range: -1.3941

Max Act: 0.9371. Min Act: -0.0000

Data Index: 916151 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 1.3941. Min Range: -1.3941

Max Act: 0.8982. Min Act: -0.0000

Data Index: 456793 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 1.3941. Min Range: -1.3941

Max Act: 0.8418. Min Act: -0.0000

Data Index: 332280 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 1.3941. Min Range: -1.3941

Max Act: 0.8294. Min Act: -0.0000

Data Index: 838077 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 1.3941. Min Range: -1.3941

Max Act: 0.8296. Min Act: -0.0000

Data Index: 912248 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 1.3941. Min Range: -1.3941

Max Act: 0.8141. Min Act: -0.0000

Data Index: 82452 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 1.3941. Min Range: -1.3941

Max Act: 0.8083. Min Act: -0.0000

Data Index: 189645 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 1.3941. Min Range: -1.3941

Max Act: 0.8069. Min Act: 0.0000

Data Index: 1277919 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 1.3941. Min Range: -1.3941

Max Act: 0.8047. Min Act: -0.0000

Data Index: 627611 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 1.3941. Min Range: -1.3941

Max Act: 0.7524. Min Act: -0.0000

Data Index: 415204 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 1.3941. Min Range: -1.3941

Max Act: 0.7395. Min Act: -0.0000

Data Index: 795432 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 1.3941. Min Range: -1.3941

Max Act: 0.7502. Min Act: -0.0000

Data Index: 453206 (C4 (Web Text))

Max Activating Token Index: 265