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

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

Neuron 4198 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2819. Min Range: -3.2819

Max Act: 3.2819. Min Act: -0.0002

Data Index: 257530 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 3.2819. Min Range: -3.2819

Max Act: 2.5888. Min Act: -0.0002

Data Index: 1195781 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 3.2819. Min Range: -3.2819

Max Act: 2.3473. Min Act: -0.0002

Data Index: 1116016 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 3.2819. Min Range: -3.2819

Max Act: 2.4553. Min Act: -0.0002

Data Index: 1210903 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 3.2819. Min Range: -3.2819

Max Act: 2.3542. Min Act: -0.0002

Data Index: 356126 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 3.2819. Min Range: -3.2819

Max Act: 2.0381. Min Act: -0.0002

Data Index: 365163 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 3.2819. Min Range: -3.2819

Max Act: 2.2091. Min Act: -0.0002

Data Index: 1265824 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 3.2819. Min Range: -3.2819

Max Act: 2.3663. Min Act: -0.0002

Data Index: 175509 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 3.2819. Min Range: -3.2819

Max Act: 2.3397. Min Act: -0.0002

Data Index: 635498 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 3.2819. Min Range: -3.2819

Max Act: 2.2860. Min Act: -0.0002

Data Index: 1296884 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 3.2819. Min Range: -3.2819

Max Act: 2.0826. Min Act: -0.0002

Data Index: 889050 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 3.2819. Min Range: -3.2819

Max Act: 2.2401. Min Act: -0.0002

Data Index: 418957 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 3.2819. Min Range: -3.2819

Max Act: 2.2062. Min Act: -0.0002

Data Index: 1231723 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 3.2819. Min Range: -3.2819

Max Act: 2.2459. Min Act: -0.0002

Data Index: 467840 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 3.2819. Min Range: -3.2819

Max Act: 2.1409. Min Act: -0.0002

Data Index: 1321785 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 3.2819. Min Range: -3.2819

Max Act: 2.1841. Min Act: -0.0002

Data Index: 544298 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 3.2819. Min Range: -3.2819

Max Act: 1.6421. Min Act: -0.0002

Data Index: 1310903 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 3.2819. Min Range: -3.2819

Max Act: 1.9701. Min Act: -0.0002

Data Index: 881917 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 3.2819. Min Range: -3.2819

Max Act: 2.1646. Min Act: -0.0002

Data Index: 888063 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 3.2819. Min Range: -3.2819

Max Act: 2.1104. Min Act: -0.0002

Data Index: 492910 (C4 (Web Text))

Max Activating Token Index: 926