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

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

Neuron 4137 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2664. Min Range: -1.2664

Max Act: 1.2624. Min Act: -0.0000

Data Index: 743179 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 1.2664. Min Range: -1.2664

Max Act: 1.2664. Min Act: -0.0000

Data Index: 4619 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 1.2664. Min Range: -1.2664

Max Act: 1.1208. Min Act: -0.0000

Data Index: 290161 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 1.2664. Min Range: -1.2664

Max Act: 1.1440. Min Act: -0.0000

Data Index: 1369714 (Python Code)

Max Activating Token Index: 969

Text #4

Max Range: 1.2664. Min Range: -1.2664

Max Act: 1.0874. Min Act: -0.0000

Data Index: 1265625 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 1.2664. Min Range: -1.2664

Max Act: 1.0711. Min Act: -0.0000

Data Index: 1008981 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 1.2664. Min Range: -1.2664

Max Act: 1.1050. Min Act: -0.0000

Data Index: 741031 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 1.2664. Min Range: -1.2664

Max Act: 1.0358. Min Act: -0.0000

Data Index: 575368 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 1.2664. Min Range: -1.2664

Max Act: 1.0017. Min Act: -0.0000

Data Index: 707366 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.9789. Min Act: -0.0000

Data Index: 1228159 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.9307. Min Act: -0.0000

Data Index: 1581772 (Python Code)

Max Activating Token Index: 632

Text #11

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.9594. Min Act: -0.0000

Data Index: 1585732 (Python Code)

Max Activating Token Index: 163

Text #12

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.9376. Min Act: -0.0000

Data Index: 688488 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.8576. Min Act: -0.0000

Data Index: 1591195 (Python Code)

Max Activating Token Index: 618

Text #14

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1085258 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.9228. Min Act: -0.0000

Data Index: 396661 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.9151. Min Act: -0.0000

Data Index: 178137 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1452887 (Python Code)

Max Activating Token Index: 479

Text #18

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1495962 (Python Code)

Max Activating Token Index: 786

Text #19

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.9769. Min Act: -0.0000

Data Index: 1628395 (Python Code)

Max Activating Token Index: 366