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

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

Neuron 3753 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: 0.0707. Min Range: -0.0707

Max Act: 0.0707. Min Act: -0.0003

Data Index: 773781 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0489. Min Act: -0.0003

Data Index: 255583 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0448. Min Act: -0.0003

Data Index: 491284 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0440. Min Act: -0.0003

Data Index: 555078 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0443. Min Act: -0.0002

Data Index: 959293 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0435. Min Act: -0.0003

Data Index: 531448 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0427. Min Act: -0.0003

Data Index: 945579 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0398. Min Act: -0.0003

Data Index: 61046 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0404. Min Act: -0.0003

Data Index: 717118 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0409. Min Act: -0.0003

Data Index: 472566 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0396. Min Act: -0.0002

Data Index: 990540 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0383. Min Act: -0.0002

Data Index: 96188 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0396. Min Act: -0.0003

Data Index: 856613 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1147141 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0380. Min Act: -0.0003

Data Index: 149478 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1334525 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0384. Min Act: -0.0003

Data Index: 301270 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0382. Min Act: -0.0003

Data Index: 853592 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1341661 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0373. Min Act: -0.0002

Data Index: 1291174 (C4 (Web Text))

Max Activating Token Index: 258