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

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

Neuron 2894 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2824. Min Range: -4.2824

Max Act: 4.2824. Min Act: -0.0000

Data Index: 1287233 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 4.2824. Min Range: -4.2824

Max Act: 4.2782. Min Act: -0.0000

Data Index: 621809 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 4.2824. Min Range: -4.2824

Max Act: 4.1425. Min Act: -0.0000

Data Index: 976518 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 4.2824. Min Range: -4.2824

Max Act: 3.7313. Min Act: -0.0000

Data Index: 670288 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 4.2824. Min Range: -4.2824

Max Act: 3.7651. Min Act: -0.0000

Data Index: 324408 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 4.2824. Min Range: -4.2824

Max Act: 3.7328. Min Act: -0.0000

Data Index: 307161 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 4.2824. Min Range: -4.2824

Max Act: 3.7893. Min Act: -0.0000

Data Index: 846659 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 4.2824. Min Range: -4.2824

Max Act: 3.6242. Min Act: -0.0000

Data Index: 948096 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 4.2824. Min Range: -4.2824

Max Act: 3.6248. Min Act: -0.0000

Data Index: 156835 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 4.2824. Min Range: -4.2824

Max Act: 3.5881. Min Act: -0.0000

Data Index: 803751 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 4.2824. Min Range: -4.2824

Max Act: 3.5299. Min Act: -0.0000

Data Index: 774957 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 4.2824. Min Range: -4.2824

Max Act: 3.3503. Min Act: -0.0000

Data Index: 508902 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 4.2824. Min Range: -4.2824

Max Act: 3.6482. Min Act: -0.0000

Data Index: 1204920 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 4.2824. Min Range: -4.2824

Max Act: 3.4778. Min Act: -0.0000

Data Index: 17881 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 4.2824. Min Range: -4.2824

Max Act: 3.4739. Min Act: -0.0000

Data Index: 1226149 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 4.2824. Min Range: -4.2824

Max Act: 3.4655. Min Act: -0.0000

Data Index: 976451 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 4.2824. Min Range: -4.2824

Max Act: 3.7614. Min Act: -0.0000

Data Index: 535400 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 4.2824. Min Range: -4.2824

Max Act: 3.4507. Min Act: -0.0000

Data Index: 1024998 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 4.2824. Min Range: -4.2824

Max Act: 3.2422. Min Act: -0.0000

Data Index: 1265287 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 4.2824. Min Range: -4.2824

Max Act: 3.2842. Min Act: -0.0000

Data Index: 319521 (C4 (Web Text))

Max Activating Token Index: 655