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

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

Neuron 911 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6471. Min Range: -1.6471

Max Act: 1.6471. Min Act: -0.0000

Data Index: 60778 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 1.6471. Min Range: -1.6471

Max Act: 1.2179. Min Act: -0.0000

Data Index: 829133 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 1.6471. Min Range: -1.6471

Max Act: 1.2402. Min Act: -0.0000

Data Index: 585976 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 1.6471. Min Range: -1.6471

Max Act: 1.1124. Min Act: -0.0000

Data Index: 203879 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 1.6471. Min Range: -1.6471

Max Act: 1.0845. Min Act: -0.0000

Data Index: 62810 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 1.6471. Min Range: -1.6471

Max Act: 1.0771. Min Act: -0.0000

Data Index: 1262025 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 1.6471. Min Range: -1.6471

Max Act: 1.1312. Min Act: -0.0000

Data Index: 370093 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 1.6471. Min Range: -1.6471

Max Act: 1.0589. Min Act: -0.0000

Data Index: 1006639 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 1.6471. Min Range: -1.6471

Max Act: 0.9841. Min Act: -0.0000

Data Index: 103430 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 1.6471. Min Range: -1.6471

Max Act: 1.0187. Min Act: -0.0000

Data Index: 619210 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 1.6471. Min Range: -1.6471

Max Act: 0.9971. Min Act: -0.0000

Data Index: 823098 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 1.6471. Min Range: -1.6471

Max Act: 1.1047. Min Act: -0.0000

Data Index: 755095 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 1.6471. Min Range: -1.6471

Max Act: 1.0360. Min Act: -0.0000

Data Index: 1617889 (Python Code)

Max Activating Token Index: 529

Text #13

Max Range: 1.6471. Min Range: -1.6471

Max Act: 1.0600. Min Act: -0.0000

Data Index: 878171 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 1.6471. Min Range: -1.6471

Max Act: 0.9845. Min Act: -0.0000

Data Index: 641250 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 1.6471. Min Range: -1.6471

Max Act: 0.9745. Min Act: -0.0000

Data Index: 428934 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 1.6471. Min Range: -1.6471

Max Act: 0.9316. Min Act: -0.0000

Data Index: 133166 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 1.6471. Min Range: -1.6471

Max Act: 0.9474. Min Act: -0.0000

Data Index: 1564737 (Python Code)

Max Activating Token Index: 1006

Text #18

Max Range: 1.6471. Min Range: -1.6471

Max Act: 0.9493. Min Act: -0.0000

Data Index: 1385682 (Python Code)

Max Activating Token Index: 769

Text #19

Max Range: 1.6471. Min Range: -1.6471

Max Act: 0.8662. Min Act: -0.0000

Data Index: 1562084 (Python Code)

Max Activating Token Index: 752