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

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

Neuron 2031 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0631. Min Range: -1.0631

Max Act: 1.0631. Min Act: -0.0003

Data Index: 321481 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 1.0631. Min Range: -1.0631

Max Act: 1.0265. Min Act: -0.0003

Data Index: 1277218 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 1.0631. Min Range: -1.0631

Max Act: 1.0290. Min Act: -0.0003

Data Index: 259495 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8878. Min Act: -0.0003

Data Index: 303050 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.9044. Min Act: -0.0003

Data Index: 554692 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8885. Min Act: -0.0003

Data Index: 1336268 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8925. Min Act: -0.0003

Data Index: 903164 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8315. Min Act: -0.0003

Data Index: 748037 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8505. Min Act: -0.0003

Data Index: 137363 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8345. Min Act: -0.0003

Data Index: 435310 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8041. Min Act: -0.0003

Data Index: 290181 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8267. Min Act: -0.0003

Data Index: 577679 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8465. Min Act: -0.0003

Data Index: 26798 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8160. Min Act: -0.0003

Data Index: 1036800 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.7952. Min Act: -0.0003

Data Index: 73592 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.7778. Min Act: -0.0003

Data Index: 1224656 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.7938. Min Act: -0.0003

Data Index: 330647 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.7864. Min Act: -0.0003

Data Index: 1033100 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.7845. Min Act: -0.0003

Data Index: 1041745 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.7737. Min Act: -0.0003

Data Index: 319606 (C4 (Web Text))

Max Activating Token Index: 588