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

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

Neuron 3815 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1913. Min Range: -4.1913

Max Act: 4.1913. Min Act: -0.0001

Data Index: 774977 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.1913. Min Range: -4.1913

Max Act: 4.1298. Min Act: -0.0001

Data Index: 1282712 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 4.1913. Min Range: -4.1913

Max Act: 3.7103. Min Act: -0.0001

Data Index: 503878 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 4.1913. Min Range: -4.1913

Max Act: 3.8578. Min Act: -0.0001

Data Index: 1170794 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 4.1913. Min Range: -4.1913

Max Act: 3.5234. Min Act: -0.0001

Data Index: 474235 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 4.1913. Min Range: -4.1913

Max Act: 3.9213. Min Act: -0.0001

Data Index: 177467 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 4.1913. Min Range: -4.1913

Max Act: 3.4884. Min Act: -0.0001

Data Index: 901770 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 4.1913. Min Range: -4.1913

Max Act: 3.5945. Min Act: -0.0001

Data Index: 671759 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 4.1913. Min Range: -4.1913

Max Act: 3.3443. Min Act: -0.0001

Data Index: 460505 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 4.1913. Min Range: -4.1913

Max Act: 3.3317. Min Act: -0.0001

Data Index: 491693 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 4.1913. Min Range: -4.1913

Max Act: 3.5370. Min Act: -0.0001

Data Index: 938471 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 4.1913. Min Range: -4.1913

Max Act: 3.3820. Min Act: -0.0001

Data Index: 799412 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 4.1913. Min Range: -4.1913

Max Act: 3.6658. Min Act: -0.0001

Data Index: 206481 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 4.1913. Min Range: -4.1913

Max Act: 3.0439. Min Act: -0.0001

Data Index: 300014 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 4.1913. Min Range: -4.1913

Max Act: 3.3469. Min Act: -0.0001

Data Index: 1281680 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 4.1913. Min Range: -4.1913

Max Act: 3.1659. Min Act: -0.0001

Data Index: 806623 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 4.1913. Min Range: -4.1913

Max Act: 3.0289. Min Act: -0.0001

Data Index: 98807 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 4.1913. Min Range: -4.1913

Max Act: 3.2827. Min Act: -0.0001

Data Index: 575012 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 4.1913. Min Range: -4.1913

Max Act: 3.1293. Min Act: -0.0001

Data Index: 394853 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 4.1913. Min Range: -4.1913

Max Act: 3.2570. Min Act: -0.0001

Data Index: 886857 (C4 (Web Text))

Max Activating Token Index: 421