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

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

Neuron 2840 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0533. Min Act: -0.0002

Data Index: 419794 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1516680 (Python Code)

Max Activating Token Index: 916

Text #2

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0495. Min Act: -0.0002

Data Index: 10092 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0484. Min Act: -0.0002

Data Index: 137652 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0402. Min Act: -0.0002

Data Index: 428574 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1534120 (Python Code)

Max Activating Token Index: 1020

Text #6

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1224711 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1649956 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1262341 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0458. Min Act: -0.0002

Data Index: 312432 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1164628 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1215222 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0403. Min Act: -0.0002

Data Index: 204289 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1459285 (Python Code)

Max Activating Token Index: 290

Text #14

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0439. Min Act: -0.0002

Data Index: 512464 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1561664 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1401061 (Python Code)

Max Activating Token Index: 31

Text #17

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1620582 (Python Code)

Max Activating Token Index: 35

Text #18

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1531153 (Python Code)

Max Activating Token Index: 35

Text #19

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1536829 (Python Code)

Max Activating Token Index: 310