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

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

Neuron 1125 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: 3.8404. Min Range: -3.8404

Max Act: 3.8404. Min Act: -0.0000

Data Index: 529477 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 3.8404. Min Range: -3.8404

Max Act: 2.8200. Min Act: -0.0000

Data Index: 46209 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 3.8404. Min Range: -3.8404

Max Act: 2.5409. Min Act: -0.0000

Data Index: 37548 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 3.8404. Min Range: -3.8404

Max Act: 2.4925. Min Act: -0.0000

Data Index: 774041 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 3.8404. Min Range: -3.8404

Max Act: 2.4860. Min Act: -0.0000

Data Index: 392044 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 3.8404. Min Range: -3.8404

Max Act: 2.7524. Min Act: -0.0000

Data Index: 730759 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 3.8404. Min Range: -3.8404

Max Act: 2.8827. Min Act: -0.0000

Data Index: 638728 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 3.8404. Min Range: -3.8404

Max Act: 2.6134. Min Act: -0.0000

Data Index: 856004 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 3.8404. Min Range: -3.8404

Max Act: 2.6426. Min Act: -0.0000

Data Index: 709271 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 3.8404. Min Range: -3.8404

Max Act: 2.6001. Min Act: -0.0000

Data Index: 1203875 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 3.8404. Min Range: -3.8404

Max Act: 2.8328. Min Act: -0.0000

Data Index: 273166 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 3.8404. Min Range: -3.8404

Max Act: 2.5836. Min Act: -0.0000

Data Index: 85833 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 3.8404. Min Range: -3.8404

Max Act: 2.5497. Min Act: -0.0000

Data Index: 1025723 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 3.8404. Min Range: -3.8404

Max Act: 2.7086. Min Act: -0.0000

Data Index: 1085578 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 3.8404. Min Range: -3.8404

Max Act: 2.7186. Min Act: -0.0000

Data Index: 63630 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 3.8404. Min Range: -3.8404

Max Act: 2.5455. Min Act: -0.0000

Data Index: 1157514 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 3.8404. Min Range: -3.8404

Max Act: 2.6326. Min Act: -0.0000

Data Index: 1226233 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 3.8404. Min Range: -3.8404

Max Act: 2.5956. Min Act: -0.0000

Data Index: 1132898 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 3.8404. Min Range: -3.8404

Max Act: 2.6990. Min Act: -0.0000

Data Index: 418472 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 3.8404. Min Range: -3.8404

Max Act: 2.4043. Min Act: -0.0000

Data Index: 599915 (C4 (Web Text))

Max Activating Token Index: 489