Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5264 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.9603. Min Act: -0.0000

Data Index: 1337356 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.4686. Min Act: -0.0000

Data Index: 930685 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.6545. Min Act: -0.0000

Data Index: 849077 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.1053. Min Act: -0.0000

Data Index: 1566 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.6562. Min Act: -0.0000

Data Index: 478590 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.4624. Min Act: -0.0000

Data Index: 1086894 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.2784. Min Act: -0.0000

Data Index: 267971 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.1054. Min Act: -0.0000

Data Index: 920645 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 3.9603. Min Range: -3.9603

Max Act: 2.9907. Min Act: -0.0000

Data Index: 941665 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 3.9603. Min Range: -3.9603

Max Act: 2.7835. Min Act: -0.0000

Data Index: 936673 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 3.9603. Min Range: -3.9603

Max Act: 3.4589. Min Act: -0.0000

Data Index: 474155 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 3.9603. Min Range: -3.9603

Max Act: 2.5491. Min Act: -0.0001

Data Index: 782727 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 3.9603. Min Range: -3.9603

Max Act: 2.6554. Min Act: -0.0000

Data Index: 617859 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 3.9603. Min Range: -3.9603

Max Act: 2.5989. Min Act: -0.0000

Data Index: 789726 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 3.9603. Min Range: -3.9603

Max Act: 2.7079. Min Act: -0.0000

Data Index: 513892 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 3.9603. Min Range: -3.9603

Max Act: 2.8767. Min Act: -0.0000

Data Index: 529168 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 3.9603. Min Range: -3.9603

Max Act: 2.8705. Min Act: -0.0000

Data Index: 238756 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 3.9603. Min Range: -3.9603

Max Act: 2.2484. Min Act: -0.0000

Data Index: 242022 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 3.9603. Min Range: -3.9603

Max Act: 2.5687. Min Act: -0.0000

Data Index: 140466 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 3.9603. Min Range: -3.9603

Max Act: 2.6858. Min Act: -0.0000

Data Index: 162081 (C4 (Web Text))

Max Activating Token Index: 160