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

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

Neuron 3341 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.7045. Min Act: -0.0001

Data Index: 807147 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5505. Min Act: -0.0001

Data Index: 116727 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5494. Min Act: -0.0001

Data Index: 263475 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5280. Min Act: -0.0001

Data Index: 762010 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5468. Min Act: -0.0001

Data Index: 647431 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5619. Min Act: -0.0001

Data Index: 19557 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5319. Min Act: -0.0001

Data Index: 1022926 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4910. Min Act: -0.0001

Data Index: 498114 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5063. Min Act: -0.0001

Data Index: 56455 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5187. Min Act: -0.0001

Data Index: 1253108 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4829. Min Act: -0.0001

Data Index: 1248789 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5042. Min Act: -0.0001

Data Index: 800501 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4844. Min Act: -0.0001

Data Index: 816325 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5017. Min Act: -0.0001

Data Index: 621042 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4702. Min Act: -0.0001

Data Index: 229604 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4505. Min Act: -0.0001

Data Index: 843295 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4777. Min Act: -0.0001

Data Index: 712871 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4410. Min Act: -0.0001

Data Index: 936379 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4358. Min Act: -0.0001

Data Index: 907367 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4649. Min Act: -0.0001

Data Index: 732904 (C4 (Web Text))

Max Activating Token Index: 18