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

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

Neuron 2608 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1614011 (Python Code)

Max Activating Token Index: 870

Text #1

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.7284. Min Act: -0.0000

Data Index: 1477017 (Python Code)

Max Activating Token Index: 931

Text #2

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1521714 (Python Code)

Max Activating Token Index: 676

Text #3

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1435651 (Python Code)

Max Activating Token Index: 947

Text #4

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1541298 (Python Code)

Max Activating Token Index: 978

Text #5

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1541209 (Python Code)

Max Activating Token Index: 604

Text #6

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1484329 (Python Code)

Max Activating Token Index: 941

Text #7

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1596946 (Python Code)

Max Activating Token Index: 655

Text #8

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1609605 (Python Code)

Max Activating Token Index: 298

Text #9

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1461683 (Python Code)

Max Activating Token Index: 500

Text #10

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1405248 (Python Code)

Max Activating Token Index: 429

Text #11

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5053. Min Act: -0.0000

Data Index: 768743 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5283. Min Act: -0.0000

Data Index: 1606931 (Python Code)

Max Activating Token Index: 549

Text #13

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1544411 (Python Code)

Max Activating Token Index: 911

Text #14

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1648196 (Python Code)

Max Activating Token Index: 967

Text #15

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5592. Min Act: -0.0000

Data Index: 1419142 (Python Code)

Max Activating Token Index: 245

Text #16

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.4908. Min Act: -0.0000

Data Index: 1454758 (Python Code)

Max Activating Token Index: 299

Text #17

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1535646 (Python Code)

Max Activating Token Index: 723

Text #18

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1652631 (Python Code)

Max Activating Token Index: 588

Text #19

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.4713. Min Act: -0.0000

Data Index: 711909 (C4 (Web Text))

Max Activating Token Index: 553