Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2277 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9703. Min Range: -2.9703

Max Act: 2.9703. Min Act: -0.0000

Data Index: 43464 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 2.9703. Min Range: -2.9703

Max Act: 2.6609. Min Act: -0.0000

Data Index: 634523 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 2.9703. Min Range: -2.9703

Max Act: 2.5022. Min Act: -0.0000

Data Index: 1060702 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 2.9703. Min Range: -2.9703

Max Act: 2.6269. Min Act: -0.0000

Data Index: 1206792 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 2.9703. Min Range: -2.9703

Max Act: 2.7391. Min Act: -0.0000

Data Index: 697119 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 2.9703. Min Range: -2.9703

Max Act: 2.6030. Min Act: -0.0000

Data Index: 1090332 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 2.9703. Min Range: -2.9703

Max Act: 2.5244. Min Act: -0.0000

Data Index: 1213860 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 2.9703. Min Range: -2.9703

Max Act: 2.5278. Min Act: -0.0000

Data Index: 113725 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 2.9703. Min Range: -2.9703

Max Act: 2.3345. Min Act: -0.0000

Data Index: 404508 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 2.9703. Min Range: -2.9703

Max Act: 2.1762. Min Act: -0.0000

Data Index: 622213 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 2.9703. Min Range: -2.9703

Max Act: 1.9467. Min Act: -0.0000

Data Index: 969926 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 2.9703. Min Range: -2.9703

Max Act: 1.9267. Min Act: -0.0000

Data Index: 19878 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 2.9703. Min Range: -2.9703

Max Act: 1.9144. Min Act: -0.0000

Data Index: 878357 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 2.9703. Min Range: -2.9703

Max Act: 1.9446. Min Act: -0.0000

Data Index: 775310 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 2.9703. Min Range: -2.9703

Max Act: 1.8101. Min Act: -0.0000

Data Index: 330544 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 2.9703. Min Range: -2.9703

Max Act: 1.9118. Min Act: -0.0000

Data Index: 1607532 (Python Code)

Max Activating Token Index: 123

Text #16

Max Range: 2.9703. Min Range: -2.9703

Max Act: 1.8165. Min Act: -0.0000

Data Index: 1316609 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 2.9703. Min Range: -2.9703

Max Act: 1.7897. Min Act: -0.0000

Data Index: 1047334 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 2.9703. Min Range: -2.9703

Max Act: 1.7436. Min Act: -0.0000

Data Index: 1127795 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 2.9703. Min Range: -2.9703

Max Act: 1.8493. Min Act: -0.0000

Data Index: 310411 (C4 (Web Text))

Max Activating Token Index: 843