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

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

Neuron 911 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0381. Min Act: -0.0005

Data Index: 916923 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0339. Min Act: -0.0005

Data Index: 901449 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0325. Min Act: -0.0005

Data Index: 101777 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0316. Min Act: -0.0005

Data Index: 176692 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0311. Min Act: -0.0005

Data Index: 143646 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0326. Min Act: -0.0005

Data Index: 405161 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0311. Min Act: -0.0005

Data Index: 706523 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0326. Min Act: -0.0005

Data Index: 550819 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0300. Min Act: -0.0005

Data Index: 1514847 (Python Code)

Max Activating Token Index: 48

Text #9

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0290. Min Act: -0.0005

Data Index: 986396 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0298. Min Act: -0.0005

Data Index: 1200052 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0319. Min Act: -0.0005

Data Index: 472289 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0308. Min Act: -0.0005

Data Index: 485355 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0295. Min Act: -0.0005

Data Index: 1057651 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0305. Min Act: -0.0005

Data Index: 1280122 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0308. Min Act: -0.0005

Data Index: 346013 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0303. Min Act: -0.0005

Data Index: 1045066 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0297. Min Act: -0.0005

Data Index: 912584 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0285. Min Act: -0.0005

Data Index: 904892 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0282. Min Act: -0.0005

Data Index: 351679 (C4 (Web Text))

Max Activating Token Index: 596