Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3121 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.7581. Min Act: -0.0001

Data Index: 618739 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.7014. Min Act: -0.0000

Data Index: 324724 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.5752. Min Act: -0.0001

Data Index: 301655 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.5629. Min Act: -0.0000

Data Index: 403 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.5440. Min Act: -0.0001

Data Index: 71498 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.4784. Min Act: -0.0001

Data Index: 1025558 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.4875. Min Act: -0.0001

Data Index: 535856 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.4942. Min Act: -0.0000

Data Index: 25595 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.4745. Min Act: -0.0001

Data Index: 70838 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.4717. Min Act: -0.0001

Data Index: 1296939 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.4672. Min Act: -0.0001

Data Index: 361560 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.4758. Min Act: -0.0001

Data Index: 621058 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.4547. Min Act: -0.0000

Data Index: 891677 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.4504. Min Act: -0.0001

Data Index: 837008 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.4625. Min Act: -0.0000

Data Index: 47967 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.4321. Min Act: -0.0001

Data Index: 120214 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1132507 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.4278. Min Act: -0.0000

Data Index: 939487 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.4378. Min Act: -0.0001

Data Index: 1297846 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.4214. Min Act: -0.0001

Data Index: 1314910 (C4 (Web Text))

Max Activating Token Index: 386