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

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

Neuron 1848 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: 0.9291. Min Range: -0.9291

Max Act: 0.9291. Min Act: -0.0001

Data Index: 1376640 (Python Code)

Max Activating Token Index: 697

Text #1

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.9073. Min Act: -0.0000

Data Index: 1173041 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.8373. Min Act: -0.0000

Data Index: 1205496 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.8251. Min Act: -0.0000

Data Index: 409248 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.8203. Min Act: -0.0000

Data Index: 219746 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.7624. Min Act: -0.0000

Data Index: 778129 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.8401. Min Act: -0.0001

Data Index: 1476763 (Python Code)

Max Activating Token Index: 386

Text #7

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1642297 (Python Code)

Max Activating Token Index: 508

Text #8

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.7881. Min Act: -0.0001

Data Index: 1253446 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.7710. Min Act: -0.0001

Data Index: 1594513 (Python Code)

Max Activating Token Index: 730

Text #10

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.7621. Min Act: -0.0001

Data Index: 871064 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.6879. Min Act: -0.0000

Data Index: 43991 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.7395. Min Act: -0.0001

Data Index: 1627079 (Python Code)

Max Activating Token Index: 384

Text #13

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.7795. Min Act: -0.0001

Data Index: 1426233 (Python Code)

Max Activating Token Index: 688

Text #14

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.7102. Min Act: -0.0000

Data Index: 866201 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.7008. Min Act: -0.0001

Data Index: 1587286 (Python Code)

Max Activating Token Index: 440

Text #16

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.6970. Min Act: -0.0000

Data Index: 969034 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.7183. Min Act: -0.0000

Data Index: 582103 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.6844. Min Act: -0.0001

Data Index: 151497 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.7240. Min Act: -0.0001

Data Index: 1027696 (C4 (Web Text))

Max Activating Token Index: 247