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

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

Neuron 3934 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1916. Min Act: -0.0001

Data Index: 953324 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1494. Min Act: -0.0002

Data Index: 689564 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1735. Min Act: -0.0001

Data Index: 36854 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1605. Min Act: -0.0001

Data Index: 652567 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1686. Min Act: -0.0001

Data Index: 1463308 (Python Code)

Max Activating Token Index: 387

Text #5

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1687. Min Act: -0.0001

Data Index: 1001525 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1554. Min Act: -0.0001

Data Index: 1188357 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1384. Min Act: -0.0001

Data Index: 1392085 (Python Code)

Max Activating Token Index: 927

Text #8

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1544. Min Act: -0.0001

Data Index: 1057894 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1388. Min Act: -0.0001

Data Index: 431133 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1390. Min Act: -0.0001

Data Index: 479418 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1392. Min Act: -0.0001

Data Index: 443118 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1732. Min Act: -0.0001

Data Index: 1114444 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1394. Min Act: -0.0001

Data Index: 555339 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1487. Min Act: -0.0001

Data Index: 385024 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1479. Min Act: -0.0001

Data Index: 179765 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1300. Min Act: -0.0001

Data Index: 933374 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1517. Min Act: -0.0001

Data Index: 1431803 (Python Code)

Max Activating Token Index: 652

Text #18

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1521. Min Act: -0.0001

Data Index: 324426 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.1916. Min Range: -0.1916

Max Act: 0.1457. Min Act: -0.0001

Data Index: 1366527 (Python Code)

Max Activating Token Index: 184