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

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

Neuron 3993 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3574. Min Act: -0.0000

Data Index: 1013122 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3636. Min Act: -0.0000

Data Index: 189791 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3535. Min Act: -0.0000

Data Index: 204381 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3563. Min Act: -0.0000

Data Index: 999840 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3453. Min Act: -0.0000

Data Index: 299158 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3334. Min Act: -0.0000

Data Index: 1275867 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3394. Min Act: -0.0000

Data Index: 527202 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2847. Min Act: -0.0000

Data Index: 836558 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3096. Min Act: -0.0000

Data Index: 973788 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2978. Min Act: -0.0000

Data Index: 923762 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1322205 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3048. Min Act: -0.0000

Data Index: 217006 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2945. Min Act: -0.0000

Data Index: 839254 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2888. Min Act: -0.0000

Data Index: 776718 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2898. Min Act: -0.0000

Data Index: 1168839 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2695. Min Act: -0.0000

Data Index: 68226 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2566. Min Act: -0.0000

Data Index: 998128 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2681. Min Act: -0.0000

Data Index: 159574 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2690. Min Act: -0.0000

Data Index: 468480 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2585. Min Act: -0.0000

Data Index: 510166 (C4 (Web Text))

Max Activating Token Index: 274