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

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

Neuron 40 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.7798. Min Act: -0.0000

Data Index: 393657 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.7832. Min Act: -0.0000

Data Index: 1181417 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6650. Min Act: -0.0000

Data Index: 150135 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6446. Min Act: -0.0000

Data Index: 229760 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6597. Min Act: -0.0000

Data Index: 681651 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6510. Min Act: -0.0000

Data Index: 683865 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6440. Min Act: -0.0000

Data Index: 17538 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.5922. Min Act: -0.0000

Data Index: 209512 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6016. Min Act: -0.0000

Data Index: 723049 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.5852. Min Act: -0.0000

Data Index: 872066 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.5643. Min Act: -0.0000

Data Index: 522371 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.5237. Min Act: -0.0000

Data Index: 241330 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.5210. Min Act: -0.0000

Data Index: 681000 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.5700. Min Act: -0.0000

Data Index: 654370 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.5214. Min Act: -0.0000

Data Index: 234629 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.5128. Min Act: -0.0000

Data Index: 169182 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.4833. Min Act: -0.0000

Data Index: 1075855 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.5628. Min Act: -0.0000

Data Index: 388458 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1204723 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.4939. Min Act: -0.0000

Data Index: 834912 (C4 (Web Text))

Max Activating Token Index: 983