Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3307 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.3072. Min Act: -0.0000

Data Index: 298512 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.2658. Min Act: -0.0001

Data Index: 848722 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.2602. Min Act: -0.0001

Data Index: 1290763 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.2772. Min Act: -0.0001

Data Index: 1286196 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.2623. Min Act: -0.0001

Data Index: 1315857 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.2550. Min Act: -0.0000

Data Index: 826746 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.2634. Min Act: -0.0001

Data Index: 391497 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.2659. Min Act: -0.0000

Data Index: 133853 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1090358 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.2596. Min Act: -0.0001

Data Index: 1167145 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.2521. Min Act: -0.0001

Data Index: 478761 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.2514. Min Act: -0.0001

Data Index: 842633 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.2479. Min Act: -0.0000

Data Index: 772164 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.2436. Min Act: -0.0001

Data Index: 672745 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.2271. Min Act: -0.0000

Data Index: 426618 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.2261. Min Act: -0.0001

Data Index: 577699 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.2481. Min Act: -0.0001

Data Index: 990916 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.2304. Min Act: -0.0000

Data Index: 247455 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.2287. Min Act: -0.0001

Data Index: 91763 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.3072. Min Range: -0.3072

Max Act: 0.2328. Min Act: -0.0000

Data Index: 508909 (C4 (Web Text))

Max Activating Token Index: 851