Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 651 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.1064. Min Act: -0.0001

Data Index: 825517 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0983. Min Act: -0.0001

Data Index: 517345 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1180778 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0846. Min Act: -0.0001

Data Index: 139617 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0879. Min Act: -0.0001

Data Index: 812686 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0904. Min Act: -0.0001

Data Index: 1118193 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0836. Min Act: -0.0001

Data Index: 334203 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0860. Min Act: -0.0001

Data Index: 897684 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0827. Min Act: -0.0001

Data Index: 1229026 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0795. Min Act: -0.0001

Data Index: 108132 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1154399 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0834. Min Act: -0.0001

Data Index: 120925 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0811. Min Act: -0.0001

Data Index: 161557 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0795. Min Act: -0.0001

Data Index: 1294875 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0840. Min Act: -0.0001

Data Index: 331144 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0789. Min Act: -0.0001

Data Index: 267266 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0788. Min Act: -0.0001

Data Index: 458533 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1345266 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1128618 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0802. Min Act: -0.0001

Data Index: 396082 (C4 (Web Text))

Max Activating Token Index: 685