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

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

Neuron 2820 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1679. Min Range: -1.1679

Max Act: 1.1679. Min Act: -0.0000

Data Index: 792072 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 1.1679. Min Range: -1.1679

Max Act: 1.0897. Min Act: -0.0000

Data Index: 1254454 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 1.1679. Min Range: -1.1679

Max Act: 1.0347. Min Act: -0.0000

Data Index: 1154789 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.9665. Min Act: -0.0000

Data Index: 1132913 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.8696. Min Act: -0.0000

Data Index: 97364 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.8794. Min Act: -0.0000

Data Index: 926634 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.8093. Min Act: -0.0000

Data Index: 852793 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.8611. Min Act: -0.0000

Data Index: 376750 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.9202. Min Act: -0.0000

Data Index: 381412 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.7644. Min Act: -0.0000

Data Index: 579786 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.7673. Min Act: -0.0000

Data Index: 6933 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.8319. Min Act: -0.0000

Data Index: 897578 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.7917. Min Act: -0.0000

Data Index: 538684 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.7560. Min Act: -0.0000

Data Index: 123205 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.7505. Min Act: -0.0000

Data Index: 675709 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1120228 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.7706. Min Act: -0.0000

Data Index: 435196 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.7211. Min Act: -0.0000

Data Index: 299312 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.7778. Min Act: -0.0000

Data Index: 220984 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 1.1679. Min Range: -1.1679

Max Act: 0.6775. Min Act: -0.0000

Data Index: 1174461 (C4 (Web Text))

Max Activating Token Index: 216