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

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

Neuron 3975 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.4808. Min Act: -0.0000

Data Index: 701969 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.4487. Min Act: 0.0000

Data Index: 1203949 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.4191. Min Act: -0.0000

Data Index: 519320 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1068251 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1120708 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1014951 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.4011. Min Act: -0.0000

Data Index: 1155895 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3835. Min Act: -0.0000

Data Index: 593954 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1248519 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1157743 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3757. Min Act: -0.0000

Data Index: 300514 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3527. Min Act: 0.0000

Data Index: 107395 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3728. Min Act: -0.0000

Data Index: 1286357 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3927. Min Act: -0.0000

Data Index: 486374 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3689. Min Act: -0.0000

Data Index: 106794 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3690. Min Act: -0.0000

Data Index: 466052 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1160725 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3703. Min Act: -0.0000

Data Index: 930798 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3777. Min Act: -0.0000

Data Index: 1034890 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3783. Min Act: -0.0000

Data Index: 351080 (C4 (Web Text))

Max Activating Token Index: 365