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

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

Neuron 2744 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.4351. Min Act: -0.0000

Data Index: 570166 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.4147. Min Act: -0.0000

Data Index: 1356852 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3841. Min Act: -0.0000

Data Index: 539864 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.4121. Min Act: -0.0000

Data Index: 630151 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1197722 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3849. Min Act: -0.0001

Data Index: 287508 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.4118. Min Act: -0.0000

Data Index: 978306 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3770. Min Act: -0.0000

Data Index: 596418 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3774. Min Act: -0.0001

Data Index: 359858 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1350048 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3875. Min Act: -0.0000

Data Index: 854606 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3735. Min Act: -0.0000

Data Index: 871323 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3651. Min Act: -0.0000

Data Index: 883766 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3462. Min Act: -0.0000

Data Index: 628782 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3568. Min Act: -0.0000

Data Index: 98396 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3570. Min Act: -0.0000

Data Index: 631000 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3533. Min Act: -0.0000

Data Index: 1042104 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3415. Min Act: -0.0000

Data Index: 795756 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3478. Min Act: -0.0000

Data Index: 1002037 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3436. Min Act: -0.0000

Data Index: 112135 (C4 (Web Text))

Max Activating Token Index: 568