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

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

Neuron 1000 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.6775. Min Act: -0.0000

Data Index: 398038 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.6709. Min Act: -0.0000

Data Index: 338106 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.5619. Min Act: -0.0000

Data Index: 251262 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.5270. Min Act: -0.0000

Data Index: 795211 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.5192. Min Act: -0.0000

Data Index: 414181 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.5119. Min Act: -0.0000

Data Index: 423414 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.4491. Min Act: -0.0000

Data Index: 862939 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1015643 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.4600. Min Act: -0.0000

Data Index: 887770 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.4771. Min Act: -0.0000

Data Index: 980086 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.4553. Min Act: -0.0000

Data Index: 211561 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.4471. Min Act: -0.0000

Data Index: 37551 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1143925 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.4140. Min Act: -0.0000

Data Index: 480151 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.4272. Min Act: -0.0000

Data Index: 364006 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.4004. Min Act: -0.0000

Data Index: 652360 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1259463 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.4006. Min Act: -0.0000

Data Index: 361351 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1178053 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.6775. Min Range: -0.6775

Max Act: 0.3844. Min Act: -0.0000

Data Index: 20734 (C4 (Web Text))

Max Activating Token Index: 854