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

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

Neuron 1038 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: 0.8458. Min Range: -0.8458

Max Act: 0.8458. Min Act: -0.0000

Data Index: 794387 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.8386. Min Act: -0.0000

Data Index: 969817 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.8045. Min Act: -0.0000

Data Index: 151595 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7998. Min Act: -0.0000

Data Index: 872756 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7665. Min Act: -0.0000

Data Index: 978269 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7692. Min Act: -0.0000

Data Index: 295326 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7537. Min Act: -0.0000

Data Index: 489368 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7512. Min Act: -0.0000

Data Index: 455200 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7598. Min Act: -0.0000

Data Index: 1139742 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7312. Min Act: -0.0000

Data Index: 391136 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7341. Min Act: -0.0000

Data Index: 1161067 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7479. Min Act: -0.0000

Data Index: 1251368 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7292. Min Act: -0.0000

Data Index: 255241 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1191453 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7448. Min Act: -0.0000

Data Index: 1043170 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7434. Min Act: -0.0000

Data Index: 199565 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7218. Min Act: -0.0000

Data Index: 1207666 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1009423 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7400. Min Act: -0.0000

Data Index: 443915 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7227. Min Act: -0.0000

Data Index: 873343 (C4 (Web Text))

Max Activating Token Index: 771