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

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

Neuron 467 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: 1.1693. Min Range: -1.1693

Max Act: 1.1693. Min Act: -0.0003

Data Index: 163646 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0221. Min Act: -0.0003

Data Index: 643909 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.7959. Min Act: -0.0003

Data Index: 1157274 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.7928. Min Act: -0.0003

Data Index: 749851 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.7891. Min Act: -0.0003

Data Index: 31144 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.7670. Min Act: -0.0003

Data Index: 1262449 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.7014. Min Act: -0.0003

Data Index: 1211176 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.7263. Min Act: -0.0003

Data Index: 987052 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.6687. Min Act: -0.0003

Data Index: 1343598 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.7293. Min Act: -0.0003

Data Index: 917559 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.7779. Min Act: -0.0003

Data Index: 865065 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.7809. Min Act: -0.0003

Data Index: 1357564 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.7501. Min Act: -0.0003

Data Index: 518104 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.6428. Min Act: -0.0003

Data Index: 567347 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.6815. Min Act: -0.0003

Data Index: 53854 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.7191. Min Act: -0.0003

Data Index: 1235750 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.5874. Min Act: -0.0003

Data Index: 582592 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.6537. Min Act: -0.0003

Data Index: 1275943 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.6610. Min Act: -0.0003

Data Index: 335028 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.5566. Min Act: -0.0003

Data Index: 299133 (C4 (Web Text))

Max Activating Token Index: 871