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

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

Neuron 1735 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: 3.0060. Min Range: -3.0060

Max Act: 3.0060. Min Act: -0.0001

Data Index: 867616 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 3.0060. Min Range: -3.0060

Max Act: 2.9881. Min Act: -0.0000

Data Index: 608881 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 3.0060. Min Range: -3.0060

Max Act: 2.6659. Min Act: -0.0000

Data Index: 715436 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 3.0060. Min Range: -3.0060

Max Act: 2.9691. Min Act: -0.0000

Data Index: 1067612 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 3.0060. Min Range: -3.0060

Max Act: 2.7967. Min Act: -0.0000

Data Index: 514087 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 3.0060. Min Range: -3.0060

Max Act: 2.3910. Min Act: -0.0001

Data Index: 1114842 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 3.0060. Min Range: -3.0060

Max Act: 2.7849. Min Act: -0.0000

Data Index: 891688 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 3.0060. Min Range: -3.0060

Max Act: 2.5769. Min Act: -0.0001

Data Index: 149035 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 3.0060. Min Range: -3.0060

Max Act: 2.5859. Min Act: -0.0000

Data Index: 849868 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 3.0060. Min Range: -3.0060

Max Act: 2.4411. Min Act: -0.0001

Data Index: 1354015 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 3.0060. Min Range: -3.0060

Max Act: 2.2121. Min Act: -0.0001

Data Index: 745067 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 3.0060. Min Range: -3.0060

Max Act: 2.3953. Min Act: -0.0000

Data Index: 748938 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 3.0060. Min Range: -3.0060

Max Act: 2.3732. Min Act: -0.0000

Data Index: 378394 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 3.0060. Min Range: -3.0060

Max Act: 2.1388. Min Act: -0.0001

Data Index: 208226 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 3.0060. Min Range: -3.0060

Max Act: 2.3766. Min Act: -0.0000

Data Index: 1321632 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 3.0060. Min Range: -3.0060

Max Act: 2.4672. Min Act: -0.0001

Data Index: 245074 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 3.0060. Min Range: -3.0060

Max Act: 2.1733. Min Act: -0.0000

Data Index: 420022 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 3.0060. Min Range: -3.0060

Max Act: 2.1767. Min Act: -0.0001

Data Index: 17194 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 3.0060. Min Range: -3.0060

Max Act: 2.2616. Min Act: -0.0000

Data Index: 301602 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 3.0060. Min Range: -3.0060

Max Act: 2.1402. Min Act: -0.0001

Data Index: 258849 (C4 (Web Text))

Max Activating Token Index: 541