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

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

Neuron 3205 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5861. Min Range: -2.5861

Max Act: 2.5861. Min Act: -0.0000

Data Index: 1414531 (Python Code)

Max Activating Token Index: 968

Text #1

Max Range: 2.5861. Min Range: -2.5861

Max Act: 1.7151. Min Act: -0.0000

Data Index: 1588608 (Python Code)

Max Activating Token Index: 974

Text #2

Max Range: 2.5861. Min Range: -2.5861

Max Act: 1.7547. Min Act: -0.0000

Data Index: 1577411 (Python Code)

Max Activating Token Index: 363

Text #3

Max Range: 2.5861. Min Range: -2.5861

Max Act: 1.5944. Min Act: -0.0000

Data Index: 1589672 (Python Code)

Max Activating Token Index: 320

Text #4

Max Range: 2.5861. Min Range: -2.5861

Max Act: 1.5004. Min Act: -0.0000

Data Index: 1518585 (Python Code)

Max Activating Token Index: 192

Text #5

Max Range: 2.5861. Min Range: -2.5861

Max Act: 1.5842. Min Act: -0.0000

Data Index: 1399300 (Python Code)

Max Activating Token Index: 100

Text #6

Max Range: 2.5861. Min Range: -2.5861

Max Act: 1.5224. Min Act: -0.0000

Data Index: 1399629 (Python Code)

Max Activating Token Index: 546

Text #7

Max Range: 2.5861. Min Range: -2.5861

Max Act: 1.6129. Min Act: -0.0000

Data Index: 1436920 (Python Code)

Max Activating Token Index: 307

Text #8

Max Range: 2.5861. Min Range: -2.5861

Max Act: 1.5093. Min Act: -0.0000

Data Index: 1518064 (Python Code)

Max Activating Token Index: 95

Text #9

Max Range: 2.5861. Min Range: -2.5861

Max Act: 1.5657. Min Act: -0.0000

Data Index: 1551387 (Python Code)

Max Activating Token Index: 852

Text #10

Max Range: 2.5861. Min Range: -2.5861

Max Act: 1.5697. Min Act: -0.0000

Data Index: 1452296 (Python Code)

Max Activating Token Index: 645

Text #11

Max Range: 2.5861. Min Range: -2.5861

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1649663 (Python Code)

Max Activating Token Index: 389

Text #12

Max Range: 2.5861. Min Range: -2.5861

Max Act: 1.4982. Min Act: -0.0000

Data Index: 1641234 (Python Code)

Max Activating Token Index: 827

Text #13

Max Range: 2.5861. Min Range: -2.5861

Max Act: 1.3689. Min Act: -0.0000

Data Index: 1454463 (Python Code)

Max Activating Token Index: 191

Text #14

Max Range: 2.5861. Min Range: -2.5861

Max Act: 1.3602. Min Act: -0.0000

Data Index: 1554973 (Python Code)

Max Activating Token Index: 279

Text #15

Max Range: 2.5861. Min Range: -2.5861

Max Act: 1.4079. Min Act: -0.0000

Data Index: 1466319 (Python Code)

Max Activating Token Index: 85

Text #16

Max Range: 2.5861. Min Range: -2.5861

Max Act: 1.3387. Min Act: -0.0000

Data Index: 1592777 (Python Code)

Max Activating Token Index: 306

Text #17

Max Range: 2.5861. Min Range: -2.5861

Max Act: 1.3569. Min Act: -0.0000

Data Index: 1578512 (Python Code)

Max Activating Token Index: 861

Text #18

Max Range: 2.5861. Min Range: -2.5861

Max Act: 1.3557. Min Act: -0.0000

Data Index: 1477876 (Python Code)

Max Activating Token Index: 649

Text #19

Max Range: 2.5861. Min Range: -2.5861

Max Act: 1.2364. Min Act: -0.0000

Data Index: 1652060 (Python Code)

Max Activating Token Index: 994