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

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

Neuron 4674 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.2873. Min Act: -0.0001

Data Index: 769735 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.2076. Min Act: -0.0001

Data Index: 395223 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.2214. Min Act: -0.0001

Data Index: 269998 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.1428. Min Act: -0.0001

Data Index: 500926 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.1661. Min Act: -0.0001

Data Index: 602221 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.0362. Min Act: -0.0001

Data Index: 791531 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 1.2873. Min Range: -1.2873

Max Act: 0.9939. Min Act: -0.0001

Data Index: 208852 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.0456. Min Act: -0.0001

Data Index: 418682 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.2178. Min Act: -0.0001

Data Index: 195220 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.1854. Min Act: -0.0001

Data Index: 122578 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.1879. Min Act: -0.0001

Data Index: 415520 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.1476. Min Act: -0.0001

Data Index: 1322241 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 1.2873. Min Range: -1.2873

Max Act: 0.9843. Min Act: -0.0001

Data Index: 979419 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.0411. Min Act: -0.0001

Data Index: 121411 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.0172. Min Act: -0.0001

Data Index: 1169610 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.0972. Min Act: -0.0001

Data Index: 186910 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.0807. Min Act: -0.0001

Data Index: 910757 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 1.2873. Min Range: -1.2873

Max Act: 1.0046. Min Act: -0.0001

Data Index: 1015829 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 1.2873. Min Range: -1.2873

Max Act: 0.8804. Min Act: -0.0001

Data Index: 492711 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 1.2873. Min Range: -1.2873

Max Act: 0.9960. Min Act: -0.0001

Data Index: 772839 (C4 (Web Text))

Max Activating Token Index: 836