Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 404 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0540. Min Act: -0.0006

Data Index: 878764 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0527. Min Act: -0.0006

Data Index: 1218722 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0535. Min Act: -0.0006

Data Index: 991114 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0514. Min Act: -0.0006

Data Index: 465938 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0514. Min Act: -0.0006

Data Index: 1346184 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0510. Min Act: -0.0006

Data Index: 723812 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0480. Min Act: -0.0006

Data Index: 833157 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0488. Min Act: -0.0006

Data Index: 236159 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0480. Min Act: -0.0006

Data Index: 216970 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0449. Min Act: -0.0006

Data Index: 127403 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0486. Min Act: -0.0006

Data Index: 1253145 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0451. Min Act: -0.0006

Data Index: 440339 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0457. Min Act: -0.0006

Data Index: 782928 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0447. Min Act: -0.0006

Data Index: 1144658 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0468. Min Act: -0.0006

Data Index: 930315 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0441. Min Act: -0.0006

Data Index: 1256955 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0506. Min Act: -0.0006

Data Index: 737876 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0450. Min Act: -0.0006

Data Index: 1048552 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0459. Min Act: -0.0006

Data Index: 628705 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0468. Min Act: -0.0006

Data Index: 810222 (C4 (Web Text))

Max Activating Token Index: 910