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

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

Neuron 4510 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5632. Min Act: -0.0001

Data Index: 670288 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4780. Min Act: -0.0001

Data Index: 120792 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4502. Min Act: -0.0001

Data Index: 601518 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4730. Min Act: -0.0001

Data Index: 526337 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4222. Min Act: -0.0001

Data Index: 231678 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4362. Min Act: -0.0001

Data Index: 1004017 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.3999. Min Act: -0.0001

Data Index: 1334006 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.3989. Min Act: -0.0001

Data Index: 915404 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4225. Min Act: -0.0001

Data Index: 1240637 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.3902. Min Act: -0.0001

Data Index: 571959 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.3508. Min Act: -0.0001

Data Index: 1063470 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4201. Min Act: -0.0001

Data Index: 868265 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4189. Min Act: -0.0001

Data Index: 736687 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.3721. Min Act: -0.0001

Data Index: 1312601 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.3466. Min Act: -0.0001

Data Index: 525841 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.3416. Min Act: -0.0000

Data Index: 68360 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.3673. Min Act: -0.0001

Data Index: 340144 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.3528. Min Act: -0.0001

Data Index: 538501 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.3354. Min Act: -0.0001

Data Index: 672055 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.3482. Min Act: -0.0001

Data Index: 533969 (C4 (Web Text))

Max Activating Token Index: 355