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

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

Neuron 929 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4605. Min Range: -2.4605

Max Act: 2.4605. Min Act: -0.0000

Data Index: 982652 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 2.4605. Min Range: -2.4605

Max Act: 2.3938. Min Act: -0.0000

Data Index: 580291 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 2.4605. Min Range: -2.4605

Max Act: 2.2865. Min Act: -0.0000

Data Index: 84585 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 2.4605. Min Range: -2.4605

Max Act: 2.2671. Min Act: -0.0000

Data Index: 1240108 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 2.4605. Min Range: -2.4605

Max Act: 2.3848. Min Act: -0.0000

Data Index: 940566 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 2.4605. Min Range: -2.4605

Max Act: 2.3823. Min Act: -0.0000

Data Index: 1013020 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 2.4605. Min Range: -2.4605

Max Act: 2.2493. Min Act: -0.0000

Data Index: 1268712 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 2.4605. Min Range: -2.4605

Max Act: 2.3499. Min Act: -0.0000

Data Index: 1098704 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 2.4605. Min Range: -2.4605

Max Act: 2.2991. Min Act: -0.0000

Data Index: 98611 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 2.4605. Min Range: -2.4605

Max Act: 2.2833. Min Act: -0.0000

Data Index: 598645 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 2.4605. Min Range: -2.4605

Max Act: 2.2967. Min Act: -0.0000

Data Index: 865013 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 2.4605. Min Range: -2.4605

Max Act: 2.2614. Min Act: -0.0000

Data Index: 580885 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 2.4605. Min Range: -2.4605

Max Act: 2.2614. Min Act: -0.0000

Data Index: 1127532 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 2.4605. Min Range: -2.4605

Max Act: 2.2938. Min Act: -0.0000

Data Index: 1202527 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 2.4605. Min Range: -2.4605

Max Act: 2.2351. Min Act: -0.0000

Data Index: 261025 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 2.4605. Min Range: -2.4605

Max Act: 2.2946. Min Act: -0.0000

Data Index: 197695 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 2.4605. Min Range: -2.4605

Max Act: 2.1419. Min Act: -0.0000

Data Index: 15453 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.9076. Min Act: -0.0000

Data Index: 346129 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.8681. Min Act: -0.0000

Data Index: 1171079 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 2.4605. Min Range: -2.4605

Max Act: 1.8175. Min Act: -0.0000

Data Index: 1170782 (C4 (Web Text))

Max Activating Token Index: 155