Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2040 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.1657. Min Act: -0.0001

Data Index: 954902 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.2395. Min Act: -0.0001

Data Index: 855467 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.1848. Min Act: -0.0001

Data Index: 55336 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.1552. Min Act: -0.0001

Data Index: 258002 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.1506. Min Act: -0.0001

Data Index: 88000 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.1204. Min Act: -0.0001

Data Index: 321113 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0758. Min Act: -0.0001

Data Index: 361857 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0909. Min Act: -0.0001

Data Index: 52240 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9983. Min Act: -0.0001

Data Index: 670408 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0786. Min Act: -0.0001

Data Index: 438979 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.1460. Min Act: -0.0001

Data Index: 454628 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0915. Min Act: -0.0001

Data Index: 101241 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0723. Min Act: -0.0001

Data Index: 701088 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0214. Min Act: -0.0001

Data Index: 1069145 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0078. Min Act: -0.0001

Data Index: 475309 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9625. Min Act: -0.0001

Data Index: 223407 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0672. Min Act: -0.0001

Data Index: 1035287 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9349. Min Act: -0.0001

Data Index: 556559 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9735. Min Act: -0.0001

Data Index: 388787 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9522. Min Act: -0.0001

Data Index: 271013 (C4 (Web Text))

Max Activating Token Index: 521