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

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

Neuron 3128 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0628. Min Act: -0.0001

Data Index: 51683 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0607. Min Act: -0.0001

Data Index: 275125 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0601. Min Act: -0.0001

Data Index: 125915 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0584. Min Act: -0.0001

Data Index: 195415 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0534. Min Act: -0.0001

Data Index: 636405 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1348145 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0529. Min Act: -0.0001

Data Index: 101096 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1346742 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0513. Min Act: -0.0001

Data Index: 527890 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0532. Min Act: -0.0001

Data Index: 1023990 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0502. Min Act: -0.0001

Data Index: 1146758 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0494. Min Act: -0.0001

Data Index: 395543 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0497. Min Act: -0.0001

Data Index: 487619 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0489. Min Act: -0.0001

Data Index: 733032 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0486. Min Act: -0.0002

Data Index: 231797 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0526. Min Act: -0.0001

Data Index: 75483 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0474. Min Act: -0.0001

Data Index: 18296 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0483. Min Act: -0.0001

Data Index: 1099580 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0461. Min Act: -0.0002

Data Index: 442818 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0478. Min Act: -0.0001

Data Index: 747059 (C4 (Web Text))

Max Activating Token Index: 836