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

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

Neuron 950 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8426. Min Range: -1.8426

Max Act: 1.8426. Min Act: -0.0000

Data Index: 714744 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 1.8426. Min Range: -1.8426

Max Act: 1.2060. Min Act: -0.0000

Data Index: 1335404 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 1.8426. Min Range: -1.8426

Max Act: 1.2846. Min Act: -0.0000

Data Index: 1414835 (Python Code)

Max Activating Token Index: 338

Text #3

Max Range: 1.8426. Min Range: -1.8426

Max Act: 1.1105. Min Act: -0.0000

Data Index: 367747 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 1.8426. Min Range: -1.8426

Max Act: 1.0647. Min Act: -0.0000

Data Index: 713520 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 1.8426. Min Range: -1.8426

Max Act: 1.1088. Min Act: -0.0000

Data Index: 1559397 (Python Code)

Max Activating Token Index: 502

Text #6

Max Range: 1.8426. Min Range: -1.8426

Max Act: 1.0432. Min Act: -0.0000

Data Index: 108095 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 1.8426. Min Range: -1.8426

Max Act: 0.9957. Min Act: -0.0000

Data Index: 1028965 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 1.8426. Min Range: -1.8426

Max Act: 0.8702. Min Act: -0.0000

Data Index: 1579710 (Python Code)

Max Activating Token Index: 290

Text #9

Max Range: 1.8426. Min Range: -1.8426

Max Act: 0.8949. Min Act: -0.0000

Data Index: 1492885 (Python Code)

Max Activating Token Index: 613

Text #10

Max Range: 1.8426. Min Range: -1.8426

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1435506 (Python Code)

Max Activating Token Index: 750

Text #11

Max Range: 1.8426. Min Range: -1.8426

Max Act: 0.8167. Min Act: -0.0000

Data Index: 1603449 (Python Code)

Max Activating Token Index: 538

Text #12

Max Range: 1.8426. Min Range: -1.8426

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1553442 (Python Code)

Max Activating Token Index: 419

Text #13

Max Range: 1.8426. Min Range: -1.8426

Max Act: 0.6997. Min Act: -0.0000

Data Index: 780129 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 1.8426. Min Range: -1.8426

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1521823 (Python Code)

Max Activating Token Index: 363

Text #15

Max Range: 1.8426. Min Range: -1.8426

Max Act: 0.6599. Min Act: -0.0000

Data Index: 603906 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 1.8426. Min Range: -1.8426

Max Act: 0.6857. Min Act: -0.0000

Data Index: 1012850 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 1.8426. Min Range: -1.8426

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1573498 (Python Code)

Max Activating Token Index: 848

Text #18

Max Range: 1.8426. Min Range: -1.8426

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1401879 (Python Code)

Max Activating Token Index: 476

Text #19

Max Range: 1.8426. Min Range: -1.8426

Max Act: 0.6683. Min Act: -0.0000

Data Index: 1581672 (Python Code)

Max Activating Token Index: 405