Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3419 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2677. Min Act: -0.0001

Data Index: 1265247 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.7479. Min Act: -0.0001

Data Index: 787473 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.7560. Min Act: -0.0001

Data Index: 270014 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.6006. Min Act: -0.0001

Data Index: 849808 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.6412. Min Act: -0.0001

Data Index: 955984 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.3402. Min Act: -0.0001

Data Index: 419629 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.5926. Min Act: -0.0001

Data Index: 1000965 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.4529. Min Act: -0.0001

Data Index: 462035 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.3005. Min Act: -0.0001

Data Index: 352763 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.4896. Min Act: -0.0001

Data Index: 611946 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.6099. Min Act: -0.0001

Data Index: 729696 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.4311. Min Act: -0.0001

Data Index: 1254287 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.3382. Min Act: -0.0001

Data Index: 1172951 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.2161. Min Act: -0.0001

Data Index: 602232 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.2421. Min Act: -0.0001

Data Index: 759500 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.4765. Min Act: -0.0000

Data Index: 546885 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.3379. Min Act: -0.0001

Data Index: 740050 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.2039. Min Act: -0.0001

Data Index: 593662 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.3129. Min Act: -0.0001

Data Index: 965898 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 3.2677. Min Range: -3.2677

Max Act: 2.1788. Min Act: -0.0001

Data Index: 1235746 (C4 (Web Text))

Max Activating Token Index: 814