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

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

Neuron 4626 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: 3.0367. Min Range: -3.0367

Max Act: 3.0367. Min Act: -0.0000

Data Index: 975979 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.8604. Min Act: -0.0000

Data Index: 701931 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.6783. Min Act: -0.0000

Data Index: 821671 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.6240. Min Act: -0.0000

Data Index: 260413 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.6138. Min Act: -0.0000

Data Index: 798182 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.5452. Min Act: -0.0000

Data Index: 902261 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.5077. Min Act: -0.0000

Data Index: 707222 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.4736. Min Act: -0.0000

Data Index: 1131543 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.4757. Min Act: -0.0000

Data Index: 230842 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.5494. Min Act: -0.0000

Data Index: 656865 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.4550. Min Act: -0.0000

Data Index: 103974 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.3252. Min Act: -0.0000

Data Index: 492628 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.2529. Min Act: -0.0000

Data Index: 431922 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.2447. Min Act: -0.0000

Data Index: 612520 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.2331. Min Act: -0.0000

Data Index: 228260 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.3502. Min Act: -0.0000

Data Index: 611766 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.3300. Min Act: -0.0000

Data Index: 1119636 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.3216. Min Act: -0.0000

Data Index: 91669 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.2879. Min Act: -0.0000

Data Index: 757652 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.3841. Min Act: -0.0000

Data Index: 151210 (C4 (Web Text))

Max Activating Token Index: 221