Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 714 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1552. Min Range: -1.1552

Max Act: 1.1552. Min Act: -0.0001

Data Index: 1540176 (Python Code)

Max Activating Token Index: 942

Text #1

Max Range: 1.1552. Min Range: -1.1552

Max Act: 1.0100. Min Act: -0.0000

Data Index: 825878 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8387. Min Act: -0.0000

Data Index: 1230561 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8559. Min Act: -0.0000

Data Index: 440328 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1317914 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.8368. Min Act: -0.0000

Data Index: 485569 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.7881. Min Act: -0.0000

Data Index: 64915 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.7959. Min Act: -0.0000

Data Index: 1337196 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.7448. Min Act: -0.0001

Data Index: 1425375 (Python Code)

Max Activating Token Index: 972

Text #9

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.7211. Min Act: -0.0001

Data Index: 1065980 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.7402. Min Act: -0.0001

Data Index: 39566 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.7323. Min Act: -0.0000

Data Index: 6163 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.6839. Min Act: 0.0001

Data Index: 1349699 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.6996. Min Act: -0.0001

Data Index: 221633 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.6943. Min Act: -0.0000

Data Index: 954756 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.6990. Min Act: -0.0000

Data Index: 564872 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.6716. Min Act: -0.0000

Data Index: 88668 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.6931. Min Act: -0.0000

Data Index: 978022 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.6673. Min Act: -0.0001

Data Index: 1207837 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 1.1552. Min Range: -1.1552

Max Act: 0.6960. Min Act: -0.0000

Data Index: 860349 (C4 (Web Text))

Max Activating Token Index: 103