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

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

Neuron 8 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: 0.0639. Min Range: -0.0639

Max Act: 0.0639. Min Act: -0.0001

Data Index: 428121 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0522. Min Act: -0.0001

Data Index: 658247 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0548. Min Act: -0.0001

Data Index: 943227 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0458. Min Act: -0.0001

Data Index: 230737 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1273933 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0485. Min Act: -0.0001

Data Index: 281314 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0407. Min Act: -0.0001

Data Index: 434916 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0403. Min Act: -0.0001

Data Index: 1172396 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0413. Min Act: -0.0001

Data Index: 132326 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0361. Min Act: -0.0001

Data Index: 224150 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0390. Min Act: -0.0001

Data Index: 412268 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0402. Min Act: -0.0001

Data Index: 767745 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0387. Min Act: -0.0001

Data Index: 10401 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0387. Min Act: -0.0001

Data Index: 722631 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0398. Min Act: -0.0001

Data Index: 1319764 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0401. Min Act: -0.0001

Data Index: 284125 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0395. Min Act: -0.0001

Data Index: 1181640 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0379. Min Act: -0.0001

Data Index: 678188 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0405. Min Act: -0.0001

Data Index: 585419 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0388. Min Act: -0.0001

Data Index: 1139931 (C4 (Web Text))

Max Activating Token Index: 435