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

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

Neuron 2638 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.1966. Min Act: -0.0002

Data Index: 315981 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.1078. Min Act: -0.0001

Data Index: 1001820 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.1102. Min Act: -0.0001

Data Index: 405112 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.0060. Min Act: -0.0001

Data Index: 287988 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.0394. Min Act: -0.0001

Data Index: 955312 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.0539. Min Act: -0.0001

Data Index: 1215343 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.9913. Min Act: -0.0001

Data Index: 165990 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.9818. Min Act: -0.0001

Data Index: 323668 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 1.1966. Min Range: -1.1966

Max Act: 1.0566. Min Act: -0.0001

Data Index: 356876 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.9935. Min Act: -0.0001

Data Index: 473521 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.9702. Min Act: -0.0001

Data Index: 302212 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.9480. Min Act: -0.0001

Data Index: 749731 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.8970. Min Act: -0.0001

Data Index: 367014 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.9246. Min Act: -0.0001

Data Index: 143961 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.8868. Min Act: -0.0001

Data Index: 986760 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.8904. Min Act: -0.0001

Data Index: 583048 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.8867. Min Act: -0.0001

Data Index: 735447 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.9140. Min Act: -0.0001

Data Index: 79602 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.9109. Min Act: -0.0001

Data Index: 792388 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 1.1966. Min Range: -1.1966

Max Act: 0.9054. Min Act: -0.0001

Data Index: 1032735 (C4 (Web Text))

Max Activating Token Index: 132