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

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

Neuron 4993 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.9430. Min Act: 0.0000

Data Index: 615328 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.6784. Min Act: 0.0000

Data Index: 1058518 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.5902. Min Act: 0.0001

Data Index: 685380 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.5233. Min Act: -0.0000

Data Index: 909122 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.5118. Min Act: 0.0000

Data Index: 1108473 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.4496. Min Act: -0.0000

Data Index: 1357625 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.4158. Min Act: 0.0000

Data Index: 388486 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.5182. Min Act: 0.0001

Data Index: 708557 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.3462. Min Act: -0.0000

Data Index: 1215467 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.3238. Min Act: 0.0001

Data Index: 1096920 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.4304. Min Act: 0.0000

Data Index: 940446 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.2548. Min Act: 0.0000

Data Index: 634055 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.1533. Min Act: -0.0000

Data Index: 641078 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.1306. Min Act: -0.0000

Data Index: 1033858 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.2664. Min Act: 0.0000

Data Index: 889146 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.2605. Min Act: 0.0000

Data Index: 713248 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.2121. Min Act: -0.0000

Data Index: 13126 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.3287. Min Act: -0.0000

Data Index: 1309695 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.0580. Min Act: -0.0000

Data Index: 1133056 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 2.9430. Min Range: -2.9430

Max Act: 2.1335. Min Act: 0.0000

Data Index: 81649 (C4 (Web Text))

Max Activating Token Index: 563