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

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

Neuron 5325 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.4362. Min Act: -0.0000

Data Index: 329645 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.4190. Min Act: -0.0000

Data Index: 969308 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3910. Min Act: -0.0000

Data Index: 172221 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3469. Min Act: -0.0000

Data Index: 15206 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3733. Min Act: -0.0000

Data Index: 997872 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3600. Min Act: -0.0000

Data Index: 459813 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3431. Min Act: -0.0000

Data Index: 432330 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3275. Min Act: -0.0000

Data Index: 870794 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1314515 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3393. Min Act: -0.0000

Data Index: 614045 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3587. Min Act: -0.0000

Data Index: 478918 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1048934 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3408. Min Act: -0.0000

Data Index: 50305 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3299. Min Act: -0.0000

Data Index: 554726 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3313. Min Act: -0.0000

Data Index: 403546 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3536. Min Act: -0.0000

Data Index: 985550 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.2934. Min Act: -0.0000

Data Index: 69435 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3233. Min Act: -0.0000

Data Index: 53158 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3746. Min Act: -0.0000

Data Index: 879850 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3019. Min Act: -0.0000

Data Index: 307642 (C4 (Web Text))

Max Activating Token Index: 386