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

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

Neuron 1370 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.5606. Min Act: -0.0002

Data Index: 716090 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.5264. Min Act: -0.0002

Data Index: 1087078 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.5485. Min Act: -0.0002

Data Index: 533770 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4586. Min Act: -0.0001

Data Index: 1039655 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.5057. Min Act: -0.0001

Data Index: 363984 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4886. Min Act: -0.0002

Data Index: 1228754 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4940. Min Act: -0.0001

Data Index: 234775 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4831. Min Act: -0.0001

Data Index: 858235 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4968. Min Act: -0.0002

Data Index: 410268 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.5008. Min Act: -0.0001

Data Index: 466280 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.5098. Min Act: -0.0002

Data Index: 358110 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4637. Min Act: -0.0001

Data Index: 1164417 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4949. Min Act: -0.0002

Data Index: 907204 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.5445. Min Act: -0.0002

Data Index: 867575 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4734. Min Act: -0.0002

Data Index: 1128863 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.5171. Min Act: -0.0002

Data Index: 226618 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4969. Min Act: -0.0002

Data Index: 522667 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.5099. Min Act: -0.0001

Data Index: 118604 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4955. Min Act: -0.0002

Data Index: 512764 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4630. Min Act: -0.0002

Data Index: 1099745 (C4 (Web Text))

Max Activating Token Index: 701