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

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

Neuron 2187 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: 0.9874. Min Range: -0.9874

Max Act: 0.9696. Min Act: -0.0000

Data Index: 478828 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.9874. Min Act: -0.0000

Data Index: 668657 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.9343. Min Act: -0.0000

Data Index: 361428 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8423. Min Act: -0.0000

Data Index: 189694 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8579. Min Act: -0.0000

Data Index: 182416 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8905. Min Act: -0.0000

Data Index: 434062 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8890. Min Act: -0.0000

Data Index: 951959 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8973. Min Act: -0.0000

Data Index: 1294004 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8773. Min Act: -0.0000

Data Index: 443255 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8716. Min Act: -0.0000

Data Index: 202329 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8257. Min Act: -0.0000

Data Index: 295468 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.9006. Min Act: -0.0000

Data Index: 327435 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8619. Min Act: -0.0000

Data Index: 877175 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7974. Min Act: -0.0000

Data Index: 332921 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7958. Min Act: -0.0000

Data Index: 831424 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8452. Min Act: -0.0000

Data Index: 767557 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8213. Min Act: -0.0000

Data Index: 147804 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8182. Min Act: -0.0000

Data Index: 1240874 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8178. Min Act: -0.0000

Data Index: 265511 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8204. Min Act: -0.0000

Data Index: 1217847 (C4 (Web Text))

Max Activating Token Index: 939