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

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

Neuron 1053 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2579. Min Range: -2.2579

Max Act: 2.2579. Min Act: -0.0000

Data Index: 59473 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 2.2579. Min Range: -2.2579

Max Act: 1.8860. Min Act: -0.0000

Data Index: 974737 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 2.2579. Min Range: -2.2579

Max Act: 1.6358. Min Act: -0.0000

Data Index: 133926 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 2.2579. Min Range: -2.2579

Max Act: 1.2682. Min Act: -0.0000

Data Index: 572922 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 2.2579. Min Range: -2.2579

Max Act: 1.3543. Min Act: -0.0000

Data Index: 1017891 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 2.2579. Min Range: -2.2579

Max Act: 1.3438. Min Act: -0.0000

Data Index: 782746 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 2.2579. Min Range: -2.2579

Max Act: 1.3644. Min Act: -0.0000

Data Index: 795973 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 2.2579. Min Range: -2.2579

Max Act: 1.3095. Min Act: -0.0000

Data Index: 1343132 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 2.2579. Min Range: -2.2579

Max Act: 1.3680. Min Act: -0.0000

Data Index: 1324839 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 2.2579. Min Range: -2.2579

Max Act: 1.3693. Min Act: -0.0000

Data Index: 679834 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 2.2579. Min Range: -2.2579

Max Act: 1.2976. Min Act: -0.0000

Data Index: 266933 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 2.2579. Min Range: -2.2579

Max Act: 1.1721. Min Act: -0.0000

Data Index: 642935 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 2.2579. Min Range: -2.2579

Max Act: 1.1087. Min Act: -0.0000

Data Index: 1230470 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 2.2579. Min Range: -2.2579

Max Act: 1.1422. Min Act: -0.0000

Data Index: 1227781 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 2.2579. Min Range: -2.2579

Max Act: 1.2130. Min Act: -0.0000

Data Index: 1030787 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 2.2579. Min Range: -2.2579

Max Act: 1.0112. Min Act: -0.0000

Data Index: 1249596 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 2.2579. Min Range: -2.2579

Max Act: 1.1824. Min Act: -0.0000

Data Index: 1175101 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 2.2579. Min Range: -2.2579

Max Act: 1.1128. Min Act: -0.0000

Data Index: 1183633 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 2.2579. Min Range: -2.2579

Max Act: 1.1256. Min Act: -0.0000

Data Index: 1067831 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 2.2579. Min Range: -2.2579

Max Act: 0.9931. Min Act: -0.0000

Data Index: 42040 (C4 (Web Text))

Max Activating Token Index: 112