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

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

Neuron 3310 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.8129. Min Act: -0.0001

Data Index: 135061 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.7569. Min Act: -0.0001

Data Index: 258853 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.6774. Min Act: -0.0001

Data Index: 696562 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.6572. Min Act: -0.0001

Data Index: 1219465 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.6227. Min Act: -0.0001

Data Index: 1090899 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.6154. Min Act: -0.0000

Data Index: 390655 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.6269. Min Act: -0.0001

Data Index: 753850 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.6204. Min Act: -0.0001

Data Index: 1316456 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.5899. Min Act: -0.0000

Data Index: 961242 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.5700. Min Act: -0.0001

Data Index: 663582 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.5581. Min Act: -0.0001

Data Index: 1046492 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1025774 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.5733. Min Act: -0.0001

Data Index: 1115470 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.5623. Min Act: -0.0001

Data Index: 915995 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.5436. Min Act: -0.0001

Data Index: 976483 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.5039. Min Act: -0.0001

Data Index: 742973 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.5520. Min Act: -0.0001

Data Index: 881771 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.5683. Min Act: -0.0001

Data Index: 1132691 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.5448. Min Act: -0.0000

Data Index: 164626 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.5639. Min Act: -0.0001

Data Index: 897865 (C4 (Web Text))

Max Activating Token Index: 230