Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 557 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0404. Min Act: -0.0001

Data Index: 8204 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0319. Min Act: -0.0002

Data Index: 106088 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0375. Min Act: -0.0002

Data Index: 257703 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0350. Min Act: -0.0001

Data Index: 557833 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1371835 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1502148 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1502401 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1557751 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1486584 (Python Code)

Max Activating Token Index: 7

Text #9

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1617905 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1468199 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1617071 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0301. Min Act: -0.0001

Data Index: 328514 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1582174 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1398511 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1474529 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1441175 (Python Code)

Max Activating Token Index: 6

Text #17

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1393104 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1446014 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1400144 (Python Code)

Max Activating Token Index: 6