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

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

Neuron 3321 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: 4.3372. Min Range: -4.3372

Max Act: 4.3372. Min Act: -0.0000

Data Index: 761428 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 4.3372. Min Range: -4.3372

Max Act: 3.3984. Min Act: -0.0000

Data Index: 845940 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 4.3372. Min Range: -4.3372

Max Act: 3.5175. Min Act: -0.0000

Data Index: 678154 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 4.3372. Min Range: -4.3372

Max Act: 3.2634. Min Act: -0.0000

Data Index: 321508 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 4.3372. Min Range: -4.3372

Max Act: 3.6618. Min Act: -0.0000

Data Index: 984310 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 4.3372. Min Range: -4.3372

Max Act: 3.0016. Min Act: -0.0000

Data Index: 932576 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 4.3372. Min Range: -4.3372

Max Act: 3.2469. Min Act: 0.0000

Data Index: 820806 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 4.3372. Min Range: -4.3372

Max Act: 3.0699. Min Act: -0.0000

Data Index: 963784 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 4.3372. Min Range: -4.3372

Max Act: 3.0741. Min Act: 0.0001

Data Index: 962324 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 4.3372. Min Range: -4.3372

Max Act: 2.8841. Min Act: -0.0000

Data Index: 452224 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 4.3372. Min Range: -4.3372

Max Act: 2.7139. Min Act: -0.0000

Data Index: 1113993 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 4.3372. Min Range: -4.3372

Max Act: 2.4252. Min Act: -0.0000

Data Index: 1332979 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 4.3372. Min Range: -4.3372

Max Act: 2.6707. Min Act: -0.0000

Data Index: 603500 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 4.3372. Min Range: -4.3372

Max Act: 2.6849. Min Act: -0.0000

Data Index: 576346 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 4.3372. Min Range: -4.3372

Max Act: 2.7937. Min Act: -0.0000

Data Index: 1241196 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 4.3372. Min Range: -4.3372

Max Act: 2.8169. Min Act: 0.0000

Data Index: 985880 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 4.3372. Min Range: -4.3372

Max Act: 2.7351. Min Act: -0.0000

Data Index: 1046308 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 4.3372. Min Range: -4.3372

Max Act: 2.6274. Min Act: -0.0000

Data Index: 1085338 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 4.3372. Min Range: -4.3372

Max Act: 2.3511. Min Act: -0.0000

Data Index: 346128 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 4.3372. Min Range: -4.3372

Max Act: 2.8883. Min Act: -0.0000

Data Index: 632633 (C4 (Web Text))

Max Activating Token Index: 175