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

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

Neuron 253 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.7509. Min Act: -0.0001

Data Index: 262812 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6322. Min Act: -0.0001

Data Index: 1312920 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6388. Min Act: -0.0001

Data Index: 160058 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6850. Min Act: -0.0001

Data Index: 1353778 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5931. Min Act: -0.0001

Data Index: 637808 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5584. Min Act: -0.0001

Data Index: 1076404 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.4982. Min Act: -0.0001

Data Index: 711545 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5276. Min Act: -0.0001

Data Index: 1358672 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.4912. Min Act: -0.0001

Data Index: 802127 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5280. Min Act: -0.0001

Data Index: 806854 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5051. Min Act: -0.0001

Data Index: 52952 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5387. Min Act: -0.0001

Data Index: 238995 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.4915. Min Act: -0.0001

Data Index: 368710 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5124. Min Act: -0.0001

Data Index: 1068086 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5282. Min Act: -0.0001

Data Index: 345097 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.4887. Min Act: -0.0001

Data Index: 261971 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5089. Min Act: -0.0001

Data Index: 943411 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.4867. Min Act: -0.0001

Data Index: 682540 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.4843. Min Act: -0.0001

Data Index: 84999 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.4421. Min Act: -0.0001

Data Index: 343581 (C4 (Web Text))

Max Activating Token Index: 904