Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1997 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.9347. Min Act: -0.0001

Data Index: 1532925 (Python Code)

Max Activating Token Index: 622

Text #1

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.8583. Min Act: -0.0001

Data Index: 1562430 (Python Code)

Max Activating Token Index: 667

Text #2

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.8771. Min Act: -0.0001

Data Index: 1484273 (Python Code)

Max Activating Token Index: 493

Text #3

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.8243. Min Act: -0.0001

Data Index: 1561355 (Python Code)

Max Activating Token Index: 326

Text #4

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.8078. Min Act: -0.0001

Data Index: 1438333 (Python Code)

Max Activating Token Index: 171

Text #5

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.7976. Min Act: -0.0001

Data Index: 1537869 (Python Code)

Max Activating Token Index: 822

Text #6

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.7964. Min Act: -0.0001

Data Index: 1573556 (Python Code)

Max Activating Token Index: 342

Text #7

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.8028. Min Act: -0.0001

Data Index: 1369021 (Python Code)

Max Activating Token Index: 133

Text #8

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.7944. Min Act: -0.0001

Data Index: 1405042 (Python Code)

Max Activating Token Index: 333

Text #9

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.7756. Min Act: -0.0001

Data Index: 1489733 (Python Code)

Max Activating Token Index: 988

Text #10

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.7388. Min Act: -0.0001

Data Index: 1491607 (Python Code)

Max Activating Token Index: 603

Text #11

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.7939. Min Act: -0.0001

Data Index: 1397716 (Python Code)

Max Activating Token Index: 189

Text #12

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.7696. Min Act: -0.0001

Data Index: 1551744 (Python Code)

Max Activating Token Index: 112

Text #13

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.7571. Min Act: -0.0001

Data Index: 1598950 (Python Code)

Max Activating Token Index: 585

Text #14

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.7341. Min Act: -0.0001

Data Index: 1382640 (Python Code)

Max Activating Token Index: 898

Text #15

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.7607. Min Act: -0.0001

Data Index: 1579923 (Python Code)

Max Activating Token Index: 689

Text #16

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.7148. Min Act: -0.0001

Data Index: 1603593 (Python Code)

Max Activating Token Index: 477

Text #17

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.7663. Min Act: -0.0001

Data Index: 1453479 (Python Code)

Max Activating Token Index: 280

Text #18

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.7168. Min Act: -0.0001

Data Index: 1463645 (Python Code)

Max Activating Token Index: 451

Text #19

Max Range: 0.9347. Min Range: -0.9347

Max Act: 0.7114. Min Act: -0.0001

Data Index: 1465307 (Python Code)

Max Activating Token Index: 187