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

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

Neuron 3703 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1177. Min Range: -3.1177

Max Act: 3.1177. Min Act: -0.0000

Data Index: 825220 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.8346. Min Act: -0.0000

Data Index: 1528215 (Python Code)

Max Activating Token Index: 919

Text #2

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.3763. Min Act: -0.0000

Data Index: 1443439 (Python Code)

Max Activating Token Index: 973

Text #3

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.4540. Min Act: -0.0000

Data Index: 1018457 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.5449. Min Act: -0.0000

Data Index: 1424252 (Python Code)

Max Activating Token Index: 106

Text #5

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.4150. Min Act: -0.0000

Data Index: 1504140 (Python Code)

Max Activating Token Index: 11

Text #6

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.2598. Min Act: -0.0000

Data Index: 99849 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.2508. Min Act: -0.0000

Data Index: 1628395 (Python Code)

Max Activating Token Index: 997

Text #8

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.1293. Min Act: -0.0000

Data Index: 491866 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.2094. Min Act: -0.0000

Data Index: 696618 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.1515. Min Act: -0.0000

Data Index: 32439 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.3599. Min Act: -0.0000

Data Index: 609567 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.1604. Min Act: -0.0000

Data Index: 708728 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.1437. Min Act: -0.0000

Data Index: 1448049 (Python Code)

Max Activating Token Index: 562

Text #14

Max Range: 3.1177. Min Range: -3.1177

Max Act: 1.9064. Min Act: -0.0001

Data Index: 1424127 (Python Code)

Max Activating Token Index: 141

Text #15

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.0287. Min Act: -0.0000

Data Index: 1628594 (Python Code)

Max Activating Token Index: 150

Text #16

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.0323. Min Act: -0.0001

Data Index: 1592433 (Python Code)

Max Activating Token Index: 386

Text #17

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.2294. Min Act: -0.0000

Data Index: 1380640 (Python Code)

Max Activating Token Index: 499

Text #18

Max Range: 3.1177. Min Range: -3.1177

Max Act: 1.9924. Min Act: -0.0000

Data Index: 29026 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.2636. Min Act: -0.0000

Data Index: 757223 (C4 (Web Text))

Max Activating Token Index: 837