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

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

Neuron 1014 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.7446. Min Act: -0.0001

Data Index: 224109 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.7315. Min Act: -0.0001

Data Index: 743477 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.6315. Min Act: -0.0001

Data Index: 1266561 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.6692. Min Act: -0.0001

Data Index: 185253 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.5570. Min Act: -0.0001

Data Index: 55629 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.5489. Min Act: -0.0001

Data Index: 556708 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.5458. Min Act: -0.0001

Data Index: 154937 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.4960. Min Act: -0.0001

Data Index: 1334271 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.4883. Min Act: -0.0001

Data Index: 1573207 (Python Code)

Max Activating Token Index: 173

Text #9

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.4923. Min Act: -0.0001

Data Index: 573476 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.4872. Min Act: -0.0001

Data Index: 691944 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.5603. Min Act: -0.0001

Data Index: 976859 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.5299. Min Act: -0.0001

Data Index: 876249 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.5469. Min Act: -0.0001

Data Index: 1323988 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.5035. Min Act: -0.0001

Data Index: 1356427 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.5078. Min Act: -0.0001

Data Index: 666140 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.5049. Min Act: -0.0001

Data Index: 1139720 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.5332. Min Act: -0.0001

Data Index: 421141 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.4906. Min Act: -0.0001

Data Index: 650326 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.4824. Min Act: -0.0001

Data Index: 744399 (C4 (Web Text))

Max Activating Token Index: 61