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

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

Neuron 907 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: 2.3215. Min Range: -2.3215

Max Act: 2.3215. Min Act: -0.0000

Data Index: 119047 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 2.3215. Min Range: -2.3215

Max Act: 2.0114. Min Act: -0.0000

Data Index: 1339797 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 2.3215. Min Range: -2.3215

Max Act: 1.7680. Min Act: -0.0000

Data Index: 50633 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 2.3215. Min Range: -2.3215

Max Act: 1.7884. Min Act: -0.0000

Data Index: 885321 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 2.3215. Min Range: -2.3215

Max Act: 1.7479. Min Act: -0.0000

Data Index: 934880 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 2.3215. Min Range: -2.3215

Max Act: 1.6815. Min Act: -0.0000

Data Index: 1062828 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 2.3215. Min Range: -2.3215

Max Act: 1.6582. Min Act: -0.0000

Data Index: 1353222 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 2.3215. Min Range: -2.3215

Max Act: 1.6336. Min Act: -0.0000

Data Index: 930487 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 2.3215. Min Range: -2.3215

Max Act: 1.7181. Min Act: -0.0001

Data Index: 1381590 (Python Code)

Max Activating Token Index: 961

Text #9

Max Range: 2.3215. Min Range: -2.3215

Max Act: 1.7088. Min Act: -0.0000

Data Index: 509208 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 2.3215. Min Range: -2.3215

Max Act: 1.5700. Min Act: -0.0000

Data Index: 153259 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 2.3215. Min Range: -2.3215

Max Act: 1.5519. Min Act: -0.0000

Data Index: 344884 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 2.3215. Min Range: -2.3215

Max Act: 1.5184. Min Act: -0.0000

Data Index: 720370 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 2.3215. Min Range: -2.3215

Max Act: 1.6060. Min Act: -0.0000

Data Index: 1325359 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 2.3215. Min Range: -2.3215

Max Act: 1.5080. Min Act: -0.0000

Data Index: 1005234 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 2.3215. Min Range: -2.3215

Max Act: 1.5569. Min Act: -0.0000

Data Index: 348308 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 2.3215. Min Range: -2.3215

Max Act: 1.6373. Min Act: -0.0000

Data Index: 1029478 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 2.3215. Min Range: -2.3215

Max Act: 1.5848. Min Act: -0.0000

Data Index: 1061014 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 2.3215. Min Range: -2.3215

Max Act: 1.6109. Min Act: -0.0000

Data Index: 515685 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 2.3215. Min Range: -2.3215

Max Act: 1.5030. Min Act: -0.0001

Data Index: 1088306 (C4 (Web Text))

Max Activating Token Index: 787