Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1281 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1876. Min Act: -0.0001

Data Index: 900632 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1922. Min Act: -0.0001

Data Index: 1016825 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1882. Min Act: -0.0001

Data Index: 1005625 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1598. Min Act: -0.0001

Data Index: 1313969 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1530. Min Act: -0.0001

Data Index: 179620 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1584. Min Act: -0.0001

Data Index: 300499 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1384. Min Act: -0.0001

Data Index: 1085370 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1505. Min Act: -0.0001

Data Index: 920270 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1515. Min Act: -0.0001

Data Index: 929485 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1461. Min Act: -0.0001

Data Index: 318511 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1446. Min Act: -0.0001

Data Index: 892984 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1534. Min Act: -0.0001

Data Index: 602470 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1436. Min Act: -0.0001

Data Index: 492573 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1468. Min Act: -0.0001

Data Index: 66350 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1486. Min Act: -0.0001

Data Index: 465576 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1458. Min Act: -0.0001

Data Index: 649259 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1407. Min Act: -0.0001

Data Index: 23501 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1444. Min Act: -0.0001

Data Index: 1179844 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1475. Min Act: -0.0001

Data Index: 496107 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1460. Min Act: -0.0001

Data Index: 579035 (C4 (Web Text))

Max Activating Token Index: 69