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

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

Neuron 2775 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2990. Min Act: -0.0000

Data Index: 505440 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2485. Min Act: -0.0001

Data Index: 605909 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2226. Min Act: -0.0000

Data Index: 659232 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2178. Min Act: -0.0000

Data Index: 541516 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.1949. Min Act: -0.0000

Data Index: 197140 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.1974. Min Act: -0.0000

Data Index: 590227 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.2044. Min Act: -0.0000

Data Index: 7915 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.1814. Min Act: -0.0001

Data Index: 846183 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.1845. Min Act: -0.0000

Data Index: 873563 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.1907. Min Act: -0.0000

Data Index: 603494 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.1904. Min Act: -0.0000

Data Index: 27988 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.1816. Min Act: -0.0000

Data Index: 136888 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.1792. Min Act: -0.0001

Data Index: 330426 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.1842. Min Act: -0.0000

Data Index: 1146884 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.1721. Min Act: -0.0000

Data Index: 829736 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.1845. Min Act: -0.0000

Data Index: 895239 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.1786. Min Act: -0.0000

Data Index: 715151 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.1775. Min Act: -0.0000

Data Index: 452888 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.1777. Min Act: -0.0000

Data Index: 868082 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.2990. Min Range: -0.2990

Max Act: 0.1779. Min Act: -0.0000

Data Index: 366200 (C4 (Web Text))

Max Activating Token Index: 562