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

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

Neuron 64 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0563. Min Range: -1.0563

Max Act: 1.0563. Min Act: -0.0000

Data Index: 489406 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 1.0563. Min Range: -1.0563

Max Act: 1.0038. Min Act: -0.0000

Data Index: 923481 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.9257. Min Act: -0.0000

Data Index: 920038 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.9427. Min Act: -0.0000

Data Index: 1292693 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8718. Min Act: -0.0000

Data Index: 790860 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8826. Min Act: -0.0000

Data Index: 1300182 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8587. Min Act: -0.0000

Data Index: 866060 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1370179 (Python Code)

Max Activating Token Index: 399

Text #8

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8043. Min Act: -0.0000

Data Index: 72994 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8160. Min Act: -0.0000

Data Index: 1293379 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8440. Min Act: -0.0000

Data Index: 318386 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8094. Min Act: -0.0000

Data Index: 1092354 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.7837. Min Act: -0.0000

Data Index: 280819 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1292217 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.7199. Min Act: -0.0000

Data Index: 156444 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1097760 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.7526. Min Act: -0.0000

Data Index: 1459458 (Python Code)

Max Activating Token Index: 425

Text #17

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8021. Min Act: -0.0000

Data Index: 374913 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.7725. Min Act: -0.0000

Data Index: 1006890 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8294. Min Act: -0.0000

Data Index: 333957 (C4 (Web Text))

Max Activating Token Index: 879