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

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

Neuron 3113 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.8435. Min Act: -0.0000

Data Index: 604993 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.8094. Min Act: -0.0000

Data Index: 1263627 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.7960. Min Act: -0.0000

Data Index: 603876 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.8515. Min Act: -0.0000

Data Index: 251615 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.7259. Min Act: -0.0000

Data Index: 973261 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.6228. Min Act: -0.0000

Data Index: 187118 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.5368. Min Act: -0.0000

Data Index: 1484112 (Python Code)

Max Activating Token Index: 501

Text #7

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1599920 (Python Code)

Max Activating Token Index: 985

Text #8

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1591808 (Python Code)

Max Activating Token Index: 699

Text #9

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.5102. Min Act: -0.0000

Data Index: 1497244 (Python Code)

Max Activating Token Index: 867

Text #10

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1487749 (Python Code)

Max Activating Token Index: 743

Text #11

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1412298 (Python Code)

Max Activating Token Index: 751

Text #12

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.4142. Min Act: -0.0000

Data Index: 1420316 (Python Code)

Max Activating Token Index: 519

Text #13

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1513642 (Python Code)

Max Activating Token Index: 458

Text #14

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.3957. Min Act: -0.0000

Data Index: 101254 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1264554 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.3957. Min Act: -0.0000

Data Index: 1522120 (Python Code)

Max Activating Token Index: 968

Text #17

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1624895 (Python Code)

Max Activating Token Index: 957

Text #18

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.3889. Min Act: -0.0000

Data Index: 415128 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.3815. Min Act: -0.0000

Data Index: 456874 (C4 (Web Text))

Max Activating Token Index: 827