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

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

Neuron 2067 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1406. Min Act: -0.0001

Data Index: 706633 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1223. Min Act: -0.0001

Data Index: 719024 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1206. Min Act: -0.0001

Data Index: 777468 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1323617 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1638737 (Python Code)

Max Activating Token Index: 633

Text #5

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1593590 (Python Code)

Max Activating Token Index: 719

Text #6

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0982. Min Act: -0.0001

Data Index: 773856 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1070. Min Act: -0.0000

Data Index: 1466674 (Python Code)

Max Activating Token Index: 973

Text #8

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1030. Min Act: -0.0001

Data Index: 315262 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1516379 (Python Code)

Max Activating Token Index: 610

Text #10

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1464211 (Python Code)

Max Activating Token Index: 100

Text #11

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0985. Min Act: -0.0000

Data Index: 795813 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1007. Min Act: -0.0001

Data Index: 60738 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0949. Min Act: -0.0000

Data Index: 1633707 (Python Code)

Max Activating Token Index: 798

Text #14

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1596606 (Python Code)

Max Activating Token Index: 919

Text #15

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0931. Min Act: -0.0001

Data Index: 32766 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0898. Min Act: -0.0001

Data Index: 1176485 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0935. Min Act: -0.0000

Data Index: 1423217 (Python Code)

Max Activating Token Index: 613

Text #18

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0915. Min Act: -0.0000

Data Index: 1545464 (Python Code)

Max Activating Token Index: 565

Text #19

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1454296 (Python Code)

Max Activating Token Index: 474