Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1658 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.3143. Min Act: -0.0002

Data Index: 1336271 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2921. Min Act: -0.0001

Data Index: 1215015 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2834. Min Act: -0.0002

Data Index: 1131313 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2580. Min Act: -0.0002

Data Index: 1160360 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2582. Min Act: -0.0002

Data Index: 1329527 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2479. Min Act: -0.0002

Data Index: 804644 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2597. Min Act: -0.0002

Data Index: 793869 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2488. Min Act: -0.0002

Data Index: 656052 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2417. Min Act: -0.0002

Data Index: 1285280 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2445. Min Act: -0.0002

Data Index: 616236 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2424. Min Act: -0.0002

Data Index: 714544 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2418. Min Act: -0.0002

Data Index: 33337 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2335. Min Act: -0.0002

Data Index: 259265 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2495. Min Act: -0.0002

Data Index: 758390 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2410. Min Act: -0.0002

Data Index: 918970 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2454. Min Act: -0.0002

Data Index: 184589 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2369. Min Act: -0.0002

Data Index: 756598 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2430. Min Act: -0.0002

Data Index: 663170 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2303. Min Act: -0.0002

Data Index: 320273 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2296. Min Act: -0.0002

Data Index: 243815 (C4 (Web Text))

Max Activating Token Index: 989