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

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

Neuron 781 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: 2.1318. Min Range: -2.1318

Max Act: 2.1318. Min Act: -0.0000

Data Index: 990779 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 2.1318. Min Range: -2.1318

Max Act: 1.5769. Min Act: -0.0000

Data Index: 559210 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 2.1318. Min Range: -2.1318

Max Act: 1.4880. Min Act: -0.0000

Data Index: 769221 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 2.1318. Min Range: -2.1318

Max Act: 1.4830. Min Act: -0.0000

Data Index: 25632 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 2.1318. Min Range: -2.1318

Max Act: 1.3455. Min Act: -0.0000

Data Index: 403050 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 2.1318. Min Range: -2.1318

Max Act: 1.1551. Min Act: -0.0000

Data Index: 1005486 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 2.1318. Min Range: -2.1318

Max Act: 1.2175. Min Act: -0.0000

Data Index: 991885 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 2.1318. Min Range: -2.1318

Max Act: 1.3027. Min Act: -0.0000

Data Index: 612087 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 2.1318. Min Range: -2.1318

Max Act: 1.0179. Min Act: -0.0000

Data Index: 41967 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 2.1318. Min Range: -2.1318

Max Act: 1.0740. Min Act: -0.0000

Data Index: 261335 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 2.1318. Min Range: -2.1318

Max Act: 1.1389. Min Act: -0.0000

Data Index: 550392 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 2.1318. Min Range: -2.1318

Max Act: 1.1675. Min Act: -0.0000

Data Index: 665983 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 2.1318. Min Range: -2.1318

Max Act: 0.9890. Min Act: -0.0000

Data Index: 297470 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 2.1318. Min Range: -2.1318

Max Act: 1.0815. Min Act: -0.0000

Data Index: 730168 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 2.1318. Min Range: -2.1318

Max Act: 1.0984. Min Act: -0.0000

Data Index: 1335172 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 2.1318. Min Range: -2.1318

Max Act: 1.0600. Min Act: -0.0000

Data Index: 891658 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 2.1318. Min Range: -2.1318

Max Act: 1.0971. Min Act: -0.0000

Data Index: 1044258 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 2.1318. Min Range: -2.1318

Max Act: 1.0239. Min Act: -0.0000

Data Index: 473188 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 2.1318. Min Range: -2.1318

Max Act: 1.0546. Min Act: -0.0000

Data Index: 437443 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 2.1318. Min Range: -2.1318

Max Act: 0.9899. Min Act: -0.0000

Data Index: 1270680 (C4 (Web Text))

Max Activating Token Index: 412