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

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

Neuron 4915 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.6480. Min Act: -0.0001

Data Index: 216394 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.6702. Min Act: -0.0001

Data Index: 1017616 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.5542. Min Act: -0.0001

Data Index: 106474 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.4315. Min Act: -0.0001

Data Index: 62220 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.3638. Min Act: -0.0001

Data Index: 258115 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.3369. Min Act: -0.0001

Data Index: 1291143 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.2959. Min Act: -0.0001

Data Index: 1275242 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.4245. Min Act: -0.0001

Data Index: 203927 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.2000. Min Act: -0.0001

Data Index: 742855 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.3337. Min Act: -0.0001

Data Index: 944676 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.2242. Min Act: -0.0001

Data Index: 110943 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.2588. Min Act: -0.0001

Data Index: 906184 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.1704. Min Act: -0.0001

Data Index: 821531 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.1682. Min Act: -0.0001

Data Index: 1256249 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.2351. Min Act: -0.0001

Data Index: 303856 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.2453. Min Act: -0.0001

Data Index: 250322 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.1005. Min Act: -0.0001

Data Index: 415482 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.1889. Min Act: -0.0001

Data Index: 160933 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.2215. Min Act: -0.0001

Data Index: 469511 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 1.6702. Min Range: -1.6702

Max Act: 1.1231. Min Act: -0.0001

Data Index: 127579 (C4 (Web Text))

Max Activating Token Index: 698