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

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

Neuron 5037 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: 0.4724. Min Range: -0.4724

Max Act: 0.4724. Min Act: -0.0000

Data Index: 71658 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3813. Min Act: -0.0000

Data Index: 21927 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3935. Min Act: -0.0000

Data Index: 402131 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3819. Min Act: -0.0000

Data Index: 250394 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3837. Min Act: -0.0000

Data Index: 23473 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3628. Min Act: -0.0000

Data Index: 1133796 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3614. Min Act: -0.0000

Data Index: 276792 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3399. Min Act: -0.0000

Data Index: 301227 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3440. Min Act: -0.0000

Data Index: 289499 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3499. Min Act: -0.0000

Data Index: 687356 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3386. Min Act: -0.0000

Data Index: 1058855 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3410. Min Act: -0.0000

Data Index: 116526 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3402. Min Act: -0.0000

Data Index: 722892 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1059235 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3320. Min Act: -0.0000

Data Index: 1230636 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3289. Min Act: -0.0000

Data Index: 1013833 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3377. Min Act: -0.0000

Data Index: 988964 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3304. Min Act: -0.0000

Data Index: 767351 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1332040 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3273. Min Act: -0.0000

Data Index: 932959 (C4 (Web Text))

Max Activating Token Index: 36