Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1974 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6604. Min Range: -1.6604

Max Act: 1.6604. Min Act: -0.0000

Data Index: 111570 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 1.6604. Min Range: -1.6604

Max Act: 1.1922. Min Act: -0.0000

Data Index: 281972 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 1.6604. Min Range: -1.6604

Max Act: 1.1034. Min Act: -0.0000

Data Index: 156836 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 1.6604. Min Range: -1.6604

Max Act: 1.0923. Min Act: -0.0000

Data Index: 214799 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 1.6604. Min Range: -1.6604

Max Act: 1.0866. Min Act: -0.0000

Data Index: 869889 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 1.6604. Min Range: -1.6604

Max Act: 1.0773. Min Act: -0.0000

Data Index: 174659 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 1.6604. Min Range: -1.6604

Max Act: 0.9259. Min Act: -0.0000

Data Index: 632806 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 1.6604. Min Range: -1.6604

Max Act: 0.9079. Min Act: -0.0000

Data Index: 7670 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 1.6604. Min Range: -1.6604

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1232415 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 1.6604. Min Range: -1.6604

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1133406 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 1.6604. Min Range: -1.6604

Max Act: 0.8808. Min Act: -0.0000

Data Index: 269201 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 1.6604. Min Range: -1.6604

Max Act: 0.8799. Min Act: -0.0000

Data Index: 848747 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 1.6604. Min Range: -1.6604

Max Act: 0.7913. Min Act: -0.0000

Data Index: 900360 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 1.6604. Min Range: -1.6604

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1335450 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 1.6604. Min Range: -1.6604

Max Act: 0.8306. Min Act: -0.0000

Data Index: 1312946 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 1.6604. Min Range: -1.6604

Max Act: 0.8233. Min Act: -0.0000

Data Index: 388754 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 1.6604. Min Range: -1.6604

Max Act: 0.7644. Min Act: -0.0000

Data Index: 999863 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 1.6604. Min Range: -1.6604

Max Act: 0.8060. Min Act: -0.0000

Data Index: 105813 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 1.6604. Min Range: -1.6604

Max Act: 0.8016. Min Act: -0.0000

Data Index: 140731 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 1.6604. Min Range: -1.6604

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1262219 (C4 (Web Text))

Max Activating Token Index: 57