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

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

Neuron 1999 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: 0.0586. Min Range: -0.0586

Max Act: 0.0586. Min Act: -0.0003

Data Index: 42709 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0571. Min Act: -0.0003

Data Index: 190065 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0521. Min Act: -0.0003

Data Index: 367842 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0515. Min Act: -0.0003

Data Index: 98891 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0460. Min Act: -0.0003

Data Index: 1086968 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0470. Min Act: -0.0003

Data Index: 230058 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0420. Min Act: -0.0003

Data Index: 110745 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0429. Min Act: -0.0003

Data Index: 987021 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0429. Min Act: -0.0003

Data Index: 467888 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0440. Min Act: -0.0003

Data Index: 404342 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0406. Min Act: -0.0003

Data Index: 1267046 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1106655 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0427. Min Act: -0.0003

Data Index: 314493 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0391. Min Act: -0.0003

Data Index: 740324 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0412. Min Act: -0.0003

Data Index: 281867 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0388. Min Act: -0.0003

Data Index: 168597 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0403. Min Act: -0.0003

Data Index: 676738 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0426. Min Act: -0.0003

Data Index: 582598 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0405. Min Act: -0.0003

Data Index: 584950 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1303371 (C4 (Web Text))

Max Activating Token Index: 225