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

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

Neuron 852 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: 0.1772. Min Range: -0.1772

Max Act: 0.1772. Min Act: -0.0002

Data Index: 468511 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1708. Min Act: -0.0001

Data Index: 645387 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1540. Min Act: -0.0001

Data Index: 1281405 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1645. Min Act: -0.0002

Data Index: 486857 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1664. Min Act: -0.0001

Data Index: 1203955 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1537. Min Act: -0.0002

Data Index: 415128 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1587. Min Act: -0.0002

Data Index: 1230188 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1585. Min Act: -0.0001

Data Index: 1326027 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1522. Min Act: -0.0001

Data Index: 598716 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1557. Min Act: -0.0001

Data Index: 1278411 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1500. Min Act: -0.0002

Data Index: 553988 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1477. Min Act: -0.0002

Data Index: 203764 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1462. Min Act: -0.0001

Data Index: 544630 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1469. Min Act: -0.0001

Data Index: 1357895 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1535. Min Act: -0.0001

Data Index: 109801 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1516. Min Act: -0.0001

Data Index: 1064669 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1489. Min Act: -0.0001

Data Index: 187201 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1422. Min Act: -0.0001

Data Index: 2166 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1429. Min Act: -0.0001

Data Index: 1227804 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.1772. Min Range: -0.1772

Max Act: 0.1477. Min Act: -0.0001

Data Index: 32355 (C4 (Web Text))

Max Activating Token Index: 151