Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 23 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1133318 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1311359 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0474. Min Act: -0.0003

Data Index: 786507 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0443. Min Act: -0.0003

Data Index: 578566 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0449. Min Act: -0.0003

Data Index: 254243 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0436. Min Act: -0.0003

Data Index: 150976 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1074762 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0423. Min Act: -0.0003

Data Index: 404780 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0443. Min Act: -0.0004

Data Index: 360934 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0443. Min Act: -0.0003

Data Index: 867408 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1104352 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0432. Min Act: -0.0003

Data Index: 899392 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0422. Min Act: -0.0003

Data Index: 370132 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0433. Min Act: -0.0003

Data Index: 491866 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0433. Min Act: -0.0003

Data Index: 279092 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0417. Min Act: -0.0003

Data Index: 1009027 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0416. Min Act: -0.0003

Data Index: 1104204 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0421. Min Act: -0.0003

Data Index: 345860 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1241134 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0420. Min Act: -0.0003

Data Index: 452930 (C4 (Web Text))

Max Activating Token Index: 587