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

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

Neuron 4748 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1005961 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0467. Min Act: -0.0002

Data Index: 659046 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0460. Min Act: -0.0002

Data Index: 324621 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0457. Min Act: -0.0003

Data Index: 441300 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0427. Min Act: -0.0003

Data Index: 788384 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1278898 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1136074 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0421. Min Act: -0.0002

Data Index: 953296 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0436. Min Act: -0.0003

Data Index: 1257673 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1275106 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0425. Min Act: -0.0003

Data Index: 356483 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0428. Min Act: -0.0002

Data Index: 889964 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0406. Min Act: -0.0003

Data Index: 1015003 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1301589 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0412. Min Act: -0.0002

Data Index: 781186 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1195645 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0402. Min Act: -0.0002

Data Index: 468498 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1116583 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1144814 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1319360 (C4 (Web Text))

Max Activating Token Index: 98