Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 658 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.5166. Min Act: -0.0000

Data Index: 270212 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3964. Min Act: -0.0001

Data Index: 236818 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1234511 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4021. Min Act: -0.0000

Data Index: 618626 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3874. Min Act: -0.0000

Data Index: 595402 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4035. Min Act: -0.0000

Data Index: 564551 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3695. Min Act: -0.0000

Data Index: 333255 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3888. Min Act: -0.0001

Data Index: 948781 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3766. Min Act: -0.0000

Data Index: 1321598 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3608. Min Act: -0.0000

Data Index: 820688 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3717. Min Act: -0.0000

Data Index: 772259 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3592. Min Act: -0.0000

Data Index: 369509 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3690. Min Act: -0.0000

Data Index: 696931 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3675. Min Act: -0.0000

Data Index: 1117410 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3543. Min Act: -0.0001

Data Index: 570672 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3635. Min Act: -0.0001

Data Index: 1211795 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3616. Min Act: -0.0000

Data Index: 650180 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3706. Min Act: -0.0000

Data Index: 1271568 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3709. Min Act: -0.0000

Data Index: 536457 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3827. Min Act: -0.0001

Data Index: 691982 (C4 (Web Text))

Max Activating Token Index: 802