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

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

Neuron 3493 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.9941. Min Act: -0.0000

Data Index: 107686 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.9574. Min Act: -0.0000

Data Index: 391096 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.9232. Min Act: -0.0000

Data Index: 66827 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1491341 (Python Code)

Max Activating Token Index: 243

Text #4

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8800. Min Act: -0.0000

Data Index: 1494073 (Python Code)

Max Activating Token Index: 357

Text #5

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.9074. Min Act: -0.0000

Data Index: 1413146 (Python Code)

Max Activating Token Index: 104

Text #6

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8608. Min Act: -0.0000

Data Index: 1625856 (Python Code)

Max Activating Token Index: 483

Text #7

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8453. Min Act: -0.0000

Data Index: 536140 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8105. Min Act: -0.0000

Data Index: 1638369 (Python Code)

Max Activating Token Index: 508

Text #9

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1417731 (Python Code)

Max Activating Token Index: 506

Text #10

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8384. Min Act: -0.0000

Data Index: 1550295 (Python Code)

Max Activating Token Index: 75

Text #11

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8460. Min Act: -0.0000

Data Index: 634115 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1467624 (Python Code)

Max Activating Token Index: 435

Text #13

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1375593 (Python Code)

Max Activating Token Index: 607

Text #14

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1561908 (Python Code)

Max Activating Token Index: 437

Text #15

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7079. Min Act: -0.0000

Data Index: 215509 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7539. Min Act: -0.0000

Data Index: 603205 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1034994 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1638941 (Python Code)

Max Activating Token Index: 374

Text #19

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7106. Min Act: -0.0000

Data Index: 155522 (C4 (Web Text))

Max Activating Token Index: 768