Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1284 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0802. Min Act: -0.0003

Data Index: 399333 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0749. Min Act: -0.0003

Data Index: 587246 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0738. Min Act: -0.0003

Data Index: 1105556 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0658. Min Act: -0.0003

Data Index: 797414 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0624. Min Act: -0.0003

Data Index: 187573 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0714. Min Act: -0.0003

Data Index: 301197 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0650. Min Act: -0.0003

Data Index: 827501 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0684. Min Act: -0.0003

Data Index: 8944 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0636. Min Act: -0.0003

Data Index: 862966 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0603. Min Act: -0.0003

Data Index: 858413 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0603. Min Act: -0.0003

Data Index: 958282 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0601. Min Act: -0.0003

Data Index: 238224 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0685. Min Act: -0.0003

Data Index: 751129 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0639. Min Act: -0.0003

Data Index: 64100 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0506. Min Act: -0.0003

Data Index: 738085 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0589. Min Act: -0.0003

Data Index: 578265 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0600. Min Act: -0.0003

Data Index: 1187054 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0583. Min Act: -0.0003

Data Index: 78549 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0559. Min Act: -0.0003

Data Index: 1347762 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0585. Min Act: -0.0003

Data Index: 725938 (C4 (Web Text))

Max Activating Token Index: 41