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

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

Neuron 1928 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0438. Min Act: -0.0001

Data Index: 271896 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0467. Min Act: -0.0001

Data Index: 681641 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0479. Min Act: -0.0001

Data Index: 913930 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0461. Min Act: -0.0001

Data Index: 1171888 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0460. Min Act: -0.0001

Data Index: 967381 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0422. Min Act: -0.0001

Data Index: 211268 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0407. Min Act: -0.0001

Data Index: 87666 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1329780 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0472. Min Act: -0.0001

Data Index: 564486 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0403. Min Act: -0.0001

Data Index: 183665 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0433. Min Act: -0.0001

Data Index: 205263 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0393. Min Act: -0.0001

Data Index: 608064 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1249233 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0349. Min Act: -0.0001

Data Index: 956964 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0372. Min Act: -0.0001

Data Index: 1608528 (Python Code)

Max Activating Token Index: 954

Text #15

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0408. Min Act: -0.0001

Data Index: 1081071 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0378. Min Act: -0.0001

Data Index: 1166035 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0418. Min Act: -0.0001

Data Index: 741685 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0356. Min Act: -0.0001

Data Index: 729038 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0399. Min Act: -0.0001

Data Index: 1002956 (C4 (Web Text))

Max Activating Token Index: 829