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

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

Neuron 3705 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.3364. Min Act: -0.0004

Data Index: 963805 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2976. Min Act: -0.0003

Data Index: 930097 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2923. Min Act: -0.0003

Data Index: 994492 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2898. Min Act: -0.0003

Data Index: 291908 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2786. Min Act: -0.0003

Data Index: 6184 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2957. Min Act: -0.0003

Data Index: 428905 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2852. Min Act: -0.0003

Data Index: 424 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2817. Min Act: -0.0003

Data Index: 426614 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2720. Min Act: -0.0003

Data Index: 163383 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2921. Min Act: -0.0003

Data Index: 443176 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2773. Min Act: -0.0003

Data Index: 962308 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2649. Min Act: -0.0003

Data Index: 1276143 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2824. Min Act: -0.0003

Data Index: 458038 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2721. Min Act: -0.0003

Data Index: 680505 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2681. Min Act: -0.0003

Data Index: 428275 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2686. Min Act: -0.0003

Data Index: 180902 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2688. Min Act: -0.0003

Data Index: 653259 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2756. Min Act: -0.0003

Data Index: 952819 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2674. Min Act: -0.0003

Data Index: 693103 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2637. Min Act: -0.0003

Data Index: 166045 (C4 (Web Text))

Max Activating Token Index: 811