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

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

Neuron 54 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.2743. Min Act: -0.0001

Data Index: 1119251 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.2248. Min Act: -0.0001

Data Index: 227211 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1922. Min Act: -0.0001

Data Index: 1006845 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1808. Min Act: -0.0001

Data Index: 438965 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1912. Min Act: -0.0001

Data Index: 51511 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1874. Min Act: -0.0001

Data Index: 11307 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1943. Min Act: -0.0001

Data Index: 582119 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1979. Min Act: -0.0001

Data Index: 1005275 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1966. Min Act: -0.0001

Data Index: 778216 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1907. Min Act: -0.0001

Data Index: 580178 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1890. Min Act: -0.0001

Data Index: 1235469 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1927. Min Act: -0.0001

Data Index: 1204687 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1842. Min Act: -0.0001

Data Index: 1253562 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1776. Min Act: -0.0001

Data Index: 1238926 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1826. Min Act: -0.0001

Data Index: 958018 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1874. Min Act: -0.0001

Data Index: 1332048 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1805. Min Act: -0.0001

Data Index: 758832 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1672. Min Act: -0.0001

Data Index: 1288083 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1644. Min Act: -0.0001

Data Index: 822837 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1600. Min Act: -0.0001

Data Index: 1020353 (C4 (Web Text))

Max Activating Token Index: 611