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

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

Neuron 2484 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1710. Min Act: -0.0001

Data Index: 1164013 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1764. Min Act: -0.0001

Data Index: 711926 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1694. Min Act: -0.0001

Data Index: 763564 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1680. Min Act: -0.0000

Data Index: 1325150 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1559. Min Act: -0.0000

Data Index: 438489 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1589. Min Act: -0.0001

Data Index: 1245558 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1420. Min Act: -0.0000

Data Index: 579619 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1489. Min Act: -0.0001

Data Index: 293779 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1498. Min Act: -0.0001

Data Index: 902654 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1425. Min Act: -0.0001

Data Index: 451970 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1447. Min Act: -0.0000

Data Index: 878467 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1417. Min Act: -0.0001

Data Index: 1042910 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1285914 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1387. Min Act: -0.0001

Data Index: 138361 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1372. Min Act: -0.0001

Data Index: 389186 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1386. Min Act: -0.0001

Data Index: 784666 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1256. Min Act: -0.0001

Data Index: 820069 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1361. Min Act: -0.0000

Data Index: 276294 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1332. Min Act: -0.0001

Data Index: 772758 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1250. Min Act: -0.0000

Data Index: 204060 (C4 (Web Text))

Max Activating Token Index: 622