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

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

Neuron 784 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.4631. Min Act: -0.0000

Data Index: 68296 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.4011. Min Act: -0.0000

Data Index: 373781 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1133061 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.3638. Min Act: -0.0000

Data Index: 834499 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.3604. Min Act: -0.0000

Data Index: 771265 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.3442. Min Act: -0.0000

Data Index: 459799 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1261898 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.3471. Min Act: -0.0000

Data Index: 1001899 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.3466. Min Act: -0.0000

Data Index: 1018242 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.3446. Min Act: -0.0000

Data Index: 1199893 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.3552. Min Act: -0.0000

Data Index: 680548 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.3263. Min Act: -0.0000

Data Index: 868906 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1342734 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.3335. Min Act: -0.0000

Data Index: 277012 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.3327. Min Act: -0.0000

Data Index: 1299817 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.3433. Min Act: -0.0000

Data Index: 670030 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.3325. Min Act: -0.0000

Data Index: 1132653 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1352186 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.3411. Min Act: -0.0000

Data Index: 273284 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.4631. Min Range: -0.4631

Max Act: 0.3261. Min Act: -0.0000

Data Index: 119419 (C4 (Web Text))

Max Activating Token Index: 766