Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 682 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3714. Min Range: -1.3714

Max Act: 1.3714. Min Act: -0.0001

Data Index: 258014 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 1.3714. Min Range: -1.3714

Max Act: 1.0385. Min Act: -0.0001

Data Index: 346003 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 1.3714. Min Range: -1.3714

Max Act: 1.0240. Min Act: -0.0001

Data Index: 241817 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.9142. Min Act: -0.0001

Data Index: 573135 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.9724. Min Act: -0.0001

Data Index: 275786 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.9258. Min Act: -0.0001

Data Index: 142617 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.9333. Min Act: -0.0001

Data Index: 324329 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.8890. Min Act: -0.0001

Data Index: 341335 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.8379. Min Act: -0.0001

Data Index: 214556 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.7891. Min Act: -0.0001

Data Index: 140262 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.8093. Min Act: -0.0001

Data Index: 1122632 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.8092. Min Act: -0.0001

Data Index: 470306 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.7789. Min Act: -0.0001

Data Index: 1013885 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.7808. Min Act: -0.0001

Data Index: 1259131 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.7602. Min Act: -0.0001

Data Index: 510142 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.7930. Min Act: -0.0001

Data Index: 1048403 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.7183. Min Act: -0.0001

Data Index: 621844 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.7071. Min Act: -0.0001

Data Index: 325011 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.6968. Min Act: -0.0001

Data Index: 705362 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.6581. Min Act: -0.0001

Data Index: 737297 (C4 (Web Text))

Max Activating Token Index: 695