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

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

Neuron 798 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3682. Min Act: -0.0000

Data Index: 127148 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2855. Min Act: -0.0000

Data Index: 390970 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2853. Min Act: -0.0000

Data Index: 459193 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1292730 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2540. Min Act: -0.0000

Data Index: 273861 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2470. Min Act: -0.0000

Data Index: 1323482 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2297. Min Act: -0.0000

Data Index: 434826 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1238031 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2211. Min Act: -0.0000

Data Index: 916716 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2369. Min Act: -0.0000

Data Index: 894397 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2467. Min Act: -0.0000

Data Index: 556977 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2146. Min Act: -0.0000

Data Index: 216704 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2374. Min Act: -0.0000

Data Index: 477870 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2370. Min Act: -0.0000

Data Index: 195910 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2234. Min Act: -0.0000

Data Index: 638640 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1035873 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2453. Min Act: -0.0000

Data Index: 240300 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2295. Min Act: -0.0000

Data Index: 139888 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2444. Min Act: -0.0000

Data Index: 21352 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.2220. Min Act: -0.0000

Data Index: 383999 (C4 (Web Text))

Max Activating Token Index: 878