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

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

Neuron 2609 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.6777. Min Act: -0.0000

Data Index: 1644288 (Python Code)

Max Activating Token Index: 350

Text #1

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.6739. Min Act: -0.0000

Data Index: 1376401 (Python Code)

Max Activating Token Index: 105

Text #2

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.6252. Min Act: -0.0000

Data Index: 1639553 (Python Code)

Max Activating Token Index: 118

Text #3

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.4585. Min Act: -0.0000

Data Index: 1403295 (Python Code)

Max Activating Token Index: 227

Text #4

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.5004. Min Act: -0.0000

Data Index: 1565130 (Python Code)

Max Activating Token Index: 268

Text #5

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.5607. Min Act: -0.0000

Data Index: 1472352 (Python Code)

Max Activating Token Index: 214

Text #6

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.4637. Min Act: -0.0000

Data Index: 1487537 (Python Code)

Max Activating Token Index: 145

Text #7

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.2389. Min Act: -0.0000

Data Index: 1644655 (Python Code)

Max Activating Token Index: 625

Text #8

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.2436. Min Act: -0.0000

Data Index: 1611878 (Python Code)

Max Activating Token Index: 155

Text #9

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.4544. Min Act: -0.0000

Data Index: 1572603 (Python Code)

Max Activating Token Index: 194

Text #10

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.2862. Min Act: -0.0000

Data Index: 1538369 (Python Code)

Max Activating Token Index: 350

Text #11

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.3038. Min Act: -0.0000

Data Index: 1388252 (Python Code)

Max Activating Token Index: 212

Text #12

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.2947. Min Act: -0.0000

Data Index: 1409195 (Python Code)

Max Activating Token Index: 709

Text #13

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.2761. Min Act: -0.0000

Data Index: 1621943 (Python Code)

Max Activating Token Index: 252

Text #14

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.2768. Min Act: -0.0000

Data Index: 1528200 (Python Code)

Max Activating Token Index: 809

Text #15

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.2813. Min Act: -0.0000

Data Index: 1611875 (Python Code)

Max Activating Token Index: 972

Text #16

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.2483. Min Act: -0.0000

Data Index: 1630187 (Python Code)

Max Activating Token Index: 250

Text #17

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.2540. Min Act: -0.0000

Data Index: 1397578 (Python Code)

Max Activating Token Index: 963

Text #18

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.2668. Min Act: -0.0000

Data Index: 1575418 (Python Code)

Max Activating Token Index: 437

Text #19

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.2604. Min Act: -0.0000

Data Index: 1603930 (Python Code)

Max Activating Token Index: 609