Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2014 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.3056. Min Act: -0.0005

Data Index: 480806 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.3011. Min Act: -0.0005

Data Index: 150858 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2964. Min Act: -0.0005

Data Index: 893475 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2867. Min Act: -0.0005

Data Index: 136136 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2944. Min Act: -0.0005

Data Index: 79698 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2813. Min Act: -0.0005

Data Index: 1031396 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2637. Min Act: -0.0005

Data Index: 299944 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2615. Min Act: -0.0005

Data Index: 367282 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2895. Min Act: -0.0005

Data Index: 710710 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2766. Min Act: -0.0005

Data Index: 800746 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2775. Min Act: -0.0005

Data Index: 61691 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2635. Min Act: -0.0005

Data Index: 657862 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2750. Min Act: -0.0005

Data Index: 573390 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2672. Min Act: -0.0005

Data Index: 1167840 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2655. Min Act: -0.0005

Data Index: 1140502 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2684. Min Act: -0.0005

Data Index: 515782 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2497. Min Act: -0.0005

Data Index: 442284 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2664. Min Act: -0.0005

Data Index: 1320465 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2743. Min Act: -0.0005

Data Index: 971460 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2835. Min Act: -0.0005

Data Index: 932505 (C4 (Web Text))

Max Activating Token Index: 608