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

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

Neuron 3881 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.3600. Min Act: -0.0000

Data Index: 97745 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.3794. Min Act: -0.0000

Data Index: 502677 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2953. Min Act: -0.0000

Data Index: 1287553 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2716. Min Act: -0.0000

Data Index: 303372 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2756. Min Act: -0.0000

Data Index: 272380 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2796. Min Act: -0.0000

Data Index: 128027 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2657. Min Act: -0.0000

Data Index: 1597930 (Python Code)

Max Activating Token Index: 827

Text #7

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2719. Min Act: -0.0000

Data Index: 1589399 (Python Code)

Max Activating Token Index: 581

Text #8

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2700. Min Act: -0.0000

Data Index: 832071 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2454. Min Act: -0.0000

Data Index: 583825 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1384305 (Python Code)

Max Activating Token Index: 213

Text #11

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2523. Min Act: -0.0000

Data Index: 1546508 (Python Code)

Max Activating Token Index: 910

Text #12

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1093959 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2473. Min Act: -0.0000

Data Index: 495154 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2572. Min Act: -0.0000

Data Index: 1618502 (Python Code)

Max Activating Token Index: 37

Text #15

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1586651 (Python Code)

Max Activating Token Index: 173

Text #16

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2301. Min Act: -0.0000

Data Index: 282089 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1529972 (Python Code)

Max Activating Token Index: 532

Text #18

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2169. Min Act: -0.0000

Data Index: 1489192 (Python Code)

Max Activating Token Index: 837

Text #19

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1081047 (C4 (Web Text))

Max Activating Token Index: 492