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

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

Neuron 351 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2863. Min Act: -0.0001

Data Index: 830478 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2706. Min Act: -0.0001

Data Index: 295576 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2960. Min Act: -0.0001

Data Index: 631645 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2899. Min Act: -0.0001

Data Index: 1279829 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2856. Min Act: -0.0001

Data Index: 370026 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2585. Min Act: -0.0001

Data Index: 895057 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2880. Min Act: -0.0001

Data Index: 1173935 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2445. Min Act: -0.0001

Data Index: 715835 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2693. Min Act: -0.0001

Data Index: 1112159 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2569. Min Act: -0.0001

Data Index: 1085931 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2783. Min Act: -0.0001

Data Index: 150292 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2665. Min Act: -0.0001

Data Index: 952628 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2631. Min Act: -0.0001

Data Index: 55707 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2487. Min Act: -0.0001

Data Index: 562011 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2502. Min Act: -0.0001

Data Index: 1192179 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2408. Min Act: -0.0001

Data Index: 956894 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2418. Min Act: -0.0001

Data Index: 279541 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2586. Min Act: -0.0001

Data Index: 1346186 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2555. Min Act: -0.0001

Data Index: 511076 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2650. Min Act: -0.0001

Data Index: 345109 (C4 (Web Text))

Max Activating Token Index: 896