Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1482 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3411. Min Act: -0.0004

Data Index: 1365275 (Python Code)

Max Activating Token Index: 282

Text #1

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3522. Min Act: -0.0004

Data Index: 1419690 (Python Code)

Max Activating Token Index: 736

Text #2

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3618. Min Act: -0.0004

Data Index: 1469326 (Python Code)

Max Activating Token Index: 626

Text #3

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3305. Min Act: -0.0004

Data Index: 1375243 (Python Code)

Max Activating Token Index: 413

Text #4

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3317. Min Act: -0.0004

Data Index: 1475184 (Python Code)

Max Activating Token Index: 987

Text #5

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2706. Min Act: -0.0004

Data Index: 1415166 (Python Code)

Max Activating Token Index: 604

Text #6

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2925. Min Act: -0.0004

Data Index: 1566632 (Python Code)

Max Activating Token Index: 859

Text #7

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2980. Min Act: -0.0004

Data Index: 1506982 (Python Code)

Max Activating Token Index: 990

Text #8

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2770. Min Act: -0.0004

Data Index: 1625104 (Python Code)

Max Activating Token Index: 408

Text #9

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2664. Min Act: -0.0004

Data Index: 1450658 (Python Code)

Max Activating Token Index: 267

Text #10

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3056. Min Act: -0.0004

Data Index: 1539252 (Python Code)

Max Activating Token Index: 920

Text #11

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3164. Min Act: -0.0004

Data Index: 1500362 (Python Code)

Max Activating Token Index: 818

Text #12

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3316. Min Act: -0.0004

Data Index: 1593271 (Python Code)

Max Activating Token Index: 571

Text #13

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2927. Min Act: -0.0004

Data Index: 1587293 (Python Code)

Max Activating Token Index: 481

Text #14

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3025. Min Act: -0.0004

Data Index: 1376461 (Python Code)

Max Activating Token Index: 463

Text #15

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2886. Min Act: -0.0004

Data Index: 1448763 (Python Code)

Max Activating Token Index: 953

Text #16

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2787. Min Act: -0.0004

Data Index: 1559604 (Python Code)

Max Activating Token Index: 58

Text #17

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2987. Min Act: -0.0004

Data Index: 1391792 (Python Code)

Max Activating Token Index: 430

Text #18

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2503. Min Act: -0.0004

Data Index: 1426201 (Python Code)

Max Activating Token Index: 536

Text #19

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2962. Min Act: -0.0004

Data Index: 1590792 (Python Code)

Max Activating Token Index: 753