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

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

Neuron 278 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: 0.9091. Min Range: -0.9091

Max Act: 0.9091. Min Act: 0.0001

Data Index: 1575750 (Python Code)

Max Activating Token Index: 209

Text #1

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.8488. Min Act: 0.0001

Data Index: 1557202 (Python Code)

Max Activating Token Index: 834

Text #2

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.8009. Min Act: 0.0001

Data Index: 1579984 (Python Code)

Max Activating Token Index: 993

Text #3

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.8261. Min Act: 0.0000

Data Index: 1561526 (Python Code)

Max Activating Token Index: 64

Text #4

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.8152. Min Act: 0.0000

Data Index: 1448370 (Python Code)

Max Activating Token Index: 299

Text #5

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7852. Min Act: 0.0001

Data Index: 1485042 (Python Code)

Max Activating Token Index: 568

Text #6

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1362074 (Python Code)

Max Activating Token Index: 777

Text #7

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7586. Min Act: 0.0001

Data Index: 1583073 (Python Code)

Max Activating Token Index: 284

Text #8

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7748. Min Act: 0.0001

Data Index: 1532803 (Python Code)

Max Activating Token Index: 64

Text #9

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7598. Min Act: 0.0001

Data Index: 1474701 (Python Code)

Max Activating Token Index: 275

Text #10

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7859. Min Act: 0.0001

Data Index: 1531421 (Python Code)

Max Activating Token Index: 190

Text #11

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7369. Min Act: -0.0000

Data Index: 1613016 (Python Code)

Max Activating Token Index: 381

Text #12

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7545. Min Act: 0.0000

Data Index: 1573284 (Python Code)

Max Activating Token Index: 519

Text #13

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1393633 (Python Code)

Max Activating Token Index: 992

Text #14

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7088. Min Act: 0.0000

Data Index: 1638000 (Python Code)

Max Activating Token Index: 197

Text #15

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7074. Min Act: -0.0000

Data Index: 1603905 (Python Code)

Max Activating Token Index: 266

Text #16

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7462. Min Act: 0.0001

Data Index: 1382416 (Python Code)

Max Activating Token Index: 994

Text #17

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.6774. Min Act: -0.0000

Data Index: 1592772 (Python Code)

Max Activating Token Index: 392

Text #18

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.6902. Min Act: 0.0000

Data Index: 1593504 (Python Code)

Max Activating Token Index: 274

Text #19

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1392881 (Python Code)

Max Activating Token Index: 464