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

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

Neuron 4002 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0556. Min Act: -0.0001

Data Index: 329655 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0460. Min Act: -0.0001

Data Index: 1113523 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0455. Min Act: -0.0001

Data Index: 655750 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0439. Min Act: -0.0001

Data Index: 700030 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0423. Min Act: -0.0001

Data Index: 97298 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0437. Min Act: -0.0001

Data Index: 113365 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0407. Min Act: -0.0001

Data Index: 1235379 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0420. Min Act: -0.0001

Data Index: 510581 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0389. Min Act: -0.0001

Data Index: 827848 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0385. Min Act: -0.0001

Data Index: 454268 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0384. Min Act: -0.0001

Data Index: 1307598 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0347. Min Act: -0.0001

Data Index: 851827 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0346. Min Act: -0.0001

Data Index: 33337 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0340. Min Act: -0.0001

Data Index: 259664 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1523407 (Python Code)

Max Activating Token Index: 572

Text #15

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0332. Min Act: -0.0001

Data Index: 124689 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0345. Min Act: -0.0001

Data Index: 65699 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0335. Min Act: -0.0001

Data Index: 1537562 (Python Code)

Max Activating Token Index: 82

Text #18

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0355. Min Act: -0.0000

Data Index: 1651573 (Python Code)

Max Activating Token Index: 81

Text #19

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0320. Min Act: -0.0001

Data Index: 324662 (C4 (Web Text))

Max Activating Token Index: 599