Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2117 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0760. Min Act: -0.0001

Data Index: 996689 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0648. Min Act: -0.0001

Data Index: 880147 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1186893 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0585. Min Act: -0.0001

Data Index: 497174 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0492. Min Act: -0.0001

Data Index: 221341 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0513. Min Act: -0.0001

Data Index: 464786 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0543. Min Act: -0.0001

Data Index: 462896 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1014125 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0520. Min Act: -0.0001

Data Index: 1189152 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0528. Min Act: -0.0001

Data Index: 648869 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0546. Min Act: -0.0001

Data Index: 849994 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0484. Min Act: -0.0001

Data Index: 670243 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0453. Min Act: -0.0001

Data Index: 1303934 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0531. Min Act: -0.0001

Data Index: 1024107 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0504. Min Act: -0.0001

Data Index: 190401 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0541. Min Act: -0.0001

Data Index: 88148 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0422. Min Act: -0.0001

Data Index: 426947 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0531. Min Act: -0.0001

Data Index: 958834 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1286064 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0496. Min Act: -0.0001

Data Index: 897594 (C4 (Web Text))

Max Activating Token Index: 62