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

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

Neuron 2356 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3627. Min Act: -0.0001

Data Index: 1024933 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3493. Min Act: -0.0000

Data Index: 457368 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2935. Min Act: -0.0001

Data Index: 937181 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3004. Min Act: -0.0001

Data Index: 1338310 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3040. Min Act: -0.0001

Data Index: 1287350 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2924. Min Act: -0.0001

Data Index: 368157 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2899. Min Act: -0.0000

Data Index: 1078974 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2821. Min Act: -0.0001

Data Index: 732847 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2702. Min Act: -0.0000

Data Index: 52420 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2800. Min Act: -0.0001

Data Index: 253752 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2734. Min Act: -0.0001

Data Index: 825856 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2721. Min Act: -0.0001

Data Index: 899589 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2608. Min Act: -0.0000

Data Index: 79591 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2684. Min Act: -0.0001

Data Index: 891996 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2654. Min Act: -0.0001

Data Index: 739279 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2592. Min Act: -0.0000

Data Index: 839241 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2516. Min Act: -0.0000

Data Index: 61469 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2503. Min Act: -0.0001

Data Index: 960732 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2425. Min Act: -0.0001

Data Index: 222407 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2366. Min Act: -0.0001

Data Index: 698142 (C4 (Web Text))

Max Activating Token Index: 614