Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3468 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.5364. Min Range: -4.5364

Max Act: 4.5364. Min Act: -0.0000

Data Index: 238549 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 4.5364. Min Range: -4.5364

Max Act: 4.1700. Min Act: -0.0001

Data Index: 79497 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 4.5364. Min Range: -4.5364

Max Act: 4.0855. Min Act: -0.0000

Data Index: 147945 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 4.5364. Min Range: -4.5364

Max Act: 4.0851. Min Act: -0.0000

Data Index: 376344 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 4.5364. Min Range: -4.5364

Max Act: 3.7980. Min Act: -0.0000

Data Index: 922084 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 4.5364. Min Range: -4.5364

Max Act: 2.9369. Min Act: -0.0001

Data Index: 148268 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 4.5364. Min Range: -4.5364

Max Act: 3.9013. Min Act: -0.0000

Data Index: 713581 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 4.5364. Min Range: -4.5364

Max Act: 3.5199. Min Act: -0.0001

Data Index: 452363 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 4.5364. Min Range: -4.5364

Max Act: 3.5111. Min Act: -0.0000

Data Index: 1050929 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 4.5364. Min Range: -4.5364

Max Act: 3.4974. Min Act: -0.0000

Data Index: 603047 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 4.5364. Min Range: -4.5364

Max Act: 3.9713. Min Act: -0.0001

Data Index: 309629 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 4.5364. Min Range: -4.5364

Max Act: 3.2983. Min Act: -0.0000

Data Index: 718681 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 4.5364. Min Range: -4.5364

Max Act: 3.5600. Min Act: -0.0000

Data Index: 212869 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 4.5364. Min Range: -4.5364

Max Act: 3.4110. Min Act: -0.0001

Data Index: 890674 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 4.5364. Min Range: -4.5364

Max Act: 3.6672. Min Act: -0.0001

Data Index: 82043 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 4.5364. Min Range: -4.5364

Max Act: 2.7708. Min Act: -0.0001

Data Index: 1165742 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 4.5364. Min Range: -4.5364

Max Act: 3.4914. Min Act: -0.0000

Data Index: 429345 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 4.5364. Min Range: -4.5364

Max Act: 3.6016. Min Act: -0.0001

Data Index: 507440 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 4.5364. Min Range: -4.5364

Max Act: 3.4713. Min Act: -0.0001

Data Index: 697390 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 4.5364. Min Range: -4.5364

Max Act: 3.3754. Min Act: -0.0000

Data Index: 216282 (C4 (Web Text))

Max Activating Token Index: 927