Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1985 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.5517. Min Act: -0.0003

Data Index: 1181187 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.4443. Min Act: -0.0003

Data Index: 101813 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.4951. Min Act: -0.0003

Data Index: 905952 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.3716. Min Act: -0.0003

Data Index: 256554 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.3121. Min Act: -0.0003

Data Index: 913488 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.3360. Min Act: -0.0003

Data Index: 508334 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.3906. Min Act: -0.0003

Data Index: 369229 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.2882. Min Act: -0.0003

Data Index: 1182174 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.3182. Min Act: -0.0003

Data Index: 368904 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.2810. Min Act: -0.0003

Data Index: 1258224 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.1332. Min Act: -0.0003

Data Index: 1214265 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.2333. Min Act: -0.0003

Data Index: 523430 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.2759. Min Act: -0.0003

Data Index: 921999 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.2320. Min Act: -0.0003

Data Index: 956507 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.2859. Min Act: -0.0003

Data Index: 994566 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.1989. Min Act: -0.0003

Data Index: 783444 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.2618. Min Act: -0.0003

Data Index: 911319 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.2192. Min Act: -0.0003

Data Index: 1341087 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.1504. Min Act: -0.0003

Data Index: 872036 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.1363. Min Act: -0.0003

Data Index: 581819 (C4 (Web Text))

Max Activating Token Index: 951