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

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

Neuron 4019 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: 0.2916. Min Range: -0.2916

Max Act: 0.2910. Min Act: -0.0001

Data Index: 303853 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2626. Min Act: -0.0001

Data Index: 81449 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2895. Min Act: -0.0001

Data Index: 233212 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2916. Min Act: -0.0001

Data Index: 1103677 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2644. Min Act: -0.0001

Data Index: 267332 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2575. Min Act: -0.0001

Data Index: 951358 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2734. Min Act: -0.0000

Data Index: 808466 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2559. Min Act: -0.0001

Data Index: 249515 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2512. Min Act: -0.0000

Data Index: 233112 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2529. Min Act: -0.0001

Data Index: 824121 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2495. Min Act: -0.0000

Data Index: 924323 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2308. Min Act: -0.0000

Data Index: 1064539 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2281. Min Act: -0.0000

Data Index: 902866 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2423. Min Act: -0.0000

Data Index: 742207 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2410. Min Act: -0.0001

Data Index: 1061368 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2407. Min Act: -0.0001

Data Index: 333239 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2316. Min Act: -0.0000

Data Index: 127595 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1033255 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2367. Min Act: -0.0001

Data Index: 1044486 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2349. Min Act: -0.0000

Data Index: 734098 (C4 (Web Text))

Max Activating Token Index: 651