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

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

Neuron 1353 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0882. Min Range: -3.0882

Max Act: 3.0882. Min Act: -0.0000

Data Index: 443508 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 3.0882. Min Range: -3.0882

Max Act: 2.5669. Min Act: -0.0000

Data Index: 1055788 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 3.0882. Min Range: -3.0882

Max Act: 2.5831. Min Act: -0.0000

Data Index: 324718 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 3.0882. Min Range: -3.0882

Max Act: 2.5039. Min Act: -0.0000

Data Index: 479759 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 3.0882. Min Range: -3.0882

Max Act: 2.3967. Min Act: -0.0000

Data Index: 1331966 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 3.0882. Min Range: -3.0882

Max Act: 2.2549. Min Act: -0.0000

Data Index: 748741 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 3.0882. Min Range: -3.0882

Max Act: 2.2521. Min Act: -0.0000

Data Index: 44612 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 3.0882. Min Range: -3.0882

Max Act: 2.5916. Min Act: -0.0000

Data Index: 1105572 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.0882. Min Range: -3.0882

Max Act: 2.2014. Min Act: -0.0000

Data Index: 682242 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 3.0882. Min Range: -3.0882

Max Act: 2.2899. Min Act: -0.0000

Data Index: 494968 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 3.0882. Min Range: -3.0882

Max Act: 2.2484. Min Act: -0.0000

Data Index: 697569 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 3.0882. Min Range: -3.0882

Max Act: 2.4853. Min Act: -0.0000

Data Index: 984945 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 3.0882. Min Range: -3.0882

Max Act: 2.2292. Min Act: -0.0000

Data Index: 519047 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 3.0882. Min Range: -3.0882

Max Act: 2.0663. Min Act: -0.0000

Data Index: 559956 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 3.0882. Min Range: -3.0882

Max Act: 2.0721. Min Act: -0.0000

Data Index: 223386 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 3.0882. Min Range: -3.0882

Max Act: 2.2611. Min Act: -0.0000

Data Index: 1226384 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 3.0882. Min Range: -3.0882

Max Act: 2.0427. Min Act: -0.0000

Data Index: 514500 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 3.0882. Min Range: -3.0882

Max Act: 2.1758. Min Act: -0.0000

Data Index: 1352242 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 3.0882. Min Range: -3.0882

Max Act: 2.0316. Min Act: -0.0000

Data Index: 1278507 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 3.0882. Min Range: -3.0882

Max Act: 2.0232. Min Act: -0.0000

Data Index: 1013681 (C4 (Web Text))

Max Activating Token Index: 261