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

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

Neuron 277 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1602278 (Python Code)

Max Activating Token Index: 224

Text #1

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1370652 (Python Code)

Max Activating Token Index: 788

Text #2

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.8535. Min Act: -0.0000

Data Index: 621230 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.7568. Min Act: -0.0000

Data Index: 1532781 (Python Code)

Max Activating Token Index: 502

Text #4

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.7713. Min Act: -0.0000

Data Index: 1624965 (Python Code)

Max Activating Token Index: 588

Text #5

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.7109. Min Act: -0.0000

Data Index: 626012 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1609123 (Python Code)

Max Activating Token Index: 514

Text #7

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1481823 (Python Code)

Max Activating Token Index: 643

Text #8

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.6932. Min Act: -0.0000

Data Index: 97036 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.7055. Min Act: -0.0000

Data Index: 1482384 (Python Code)

Max Activating Token Index: 27

Text #10

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.6780. Min Act: -0.0000

Data Index: 1525032 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1075340 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.6664. Min Act: -0.0000

Data Index: 150558 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1631398 (Python Code)

Max Activating Token Index: 60

Text #14

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.7353. Min Act: -0.0000

Data Index: 311313 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1375899 (Python Code)

Max Activating Token Index: 154

Text #16

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1583485 (Python Code)

Max Activating Token Index: 730

Text #17

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.6651. Min Act: -0.0000

Data Index: 572088 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.6076. Min Act: -0.0000

Data Index: 553885 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.9291. Min Range: -0.9291

Max Act: 0.6073. Min Act: -0.0000

Data Index: 1380724 (Python Code)

Max Activating Token Index: 7