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

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

Neuron 253 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: 5.1778. Min Range: -5.1778

Max Act: 5.1778. Min Act: -0.0000

Data Index: 482360 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 5.1778. Min Range: -5.1778

Max Act: 4.1627. Min Act: -0.0000

Data Index: 1316094 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 5.1778. Min Range: -5.1778

Max Act: 4.1532. Min Act: -0.0000

Data Index: 1135172 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 5.1778. Min Range: -5.1778

Max Act: 3.7965. Min Act: -0.0000

Data Index: 716784 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 5.1778. Min Range: -5.1778

Max Act: 3.7173. Min Act: -0.0000

Data Index: 952922 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 5.1778. Min Range: -5.1778

Max Act: 3.5811. Min Act: -0.0000

Data Index: 542998 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 5.1778. Min Range: -5.1778

Max Act: 3.3973. Min Act: -0.0000

Data Index: 54981 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 5.1778. Min Range: -5.1778

Max Act: 3.4902. Min Act: -0.0000

Data Index: 654162 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 5.1778. Min Range: -5.1778

Max Act: 3.3178. Min Act: -0.0000

Data Index: 568806 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 5.1778. Min Range: -5.1778

Max Act: 3.4749. Min Act: 0.0000

Data Index: 1226667 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 5.1778. Min Range: -5.1778

Max Act: 3.4800. Min Act: 0.0000

Data Index: 915608 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 5.1778. Min Range: -5.1778

Max Act: 3.2855. Min Act: 0.0000

Data Index: 96411 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 5.1778. Min Range: -5.1778

Max Act: 3.4204. Min Act: -0.0000

Data Index: 282640 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 5.1778. Min Range: -5.1778

Max Act: 3.3836. Min Act: 0.0000

Data Index: 259243 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 5.1778. Min Range: -5.1778

Max Act: 3.3597. Min Act: -0.0000

Data Index: 201632 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 5.1778. Min Range: -5.1778

Max Act: 3.6593. Min Act: 0.0000

Data Index: 1272389 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 5.1778. Min Range: -5.1778

Max Act: 3.3061. Min Act: -0.0000

Data Index: 1311728 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 5.1778. Min Range: -5.1778

Max Act: 3.3022. Min Act: -0.0000

Data Index: 108569 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 5.1778. Min Range: -5.1778

Max Act: 3.1043. Min Act: 0.0000

Data Index: 659743 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 5.1778. Min Range: -5.1778

Max Act: 3.2410. Min Act: -0.0000

Data Index: 797708 (C4 (Web Text))

Max Activating Token Index: 490