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

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

Neuron 17 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0576. Min Act: -0.0002

Data Index: 227432 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0455. Min Act: -0.0002

Data Index: 806435 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1254993 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0496. Min Act: -0.0002

Data Index: 77227 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0473. Min Act: -0.0002

Data Index: 693731 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0471. Min Act: -0.0002

Data Index: 388052 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0459. Min Act: -0.0002

Data Index: 305771 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0483. Min Act: -0.0002

Data Index: 113091 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1168657 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0524. Min Act: -0.0002

Data Index: 127662 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0488. Min Act: -0.0002

Data Index: 903400 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1342745 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0465. Min Act: -0.0002

Data Index: 813553 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1034898 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1354988 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0464. Min Act: -0.0002

Data Index: 624560 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1024466 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0475. Min Act: -0.0002

Data Index: 546766 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0519. Min Act: -0.0002

Data Index: 698606 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0455. Min Act: -0.0002

Data Index: 746469 (C4 (Web Text))

Max Activating Token Index: 410