Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2510 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2563. Min Range: -1.2563

Max Act: 1.2563. Min Act: -0.0000

Data Index: 1629920 (Python Code)

Max Activating Token Index: 179

Text #1

Max Range: 1.2563. Min Range: -1.2563

Max Act: 1.1490. Min Act: -0.0000

Data Index: 1606210 (Python Code)

Max Activating Token Index: 310

Text #2

Max Range: 1.2563. Min Range: -1.2563

Max Act: 1.1045. Min Act: -0.0000

Data Index: 1417019 (Python Code)

Max Activating Token Index: 23

Text #3

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1447431 (Python Code)

Max Activating Token Index: 188

Text #4

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.9594. Min Act: -0.0000

Data Index: 1468860 (Python Code)

Max Activating Token Index: 256

Text #5

Max Range: 1.2563. Min Range: -1.2563

Max Act: 1.1142. Min Act: -0.0000

Data Index: 1477141 (Python Code)

Max Activating Token Index: 433

Text #6

Max Range: 1.2563. Min Range: -1.2563

Max Act: 1.0668. Min Act: -0.0000

Data Index: 1490438 (Python Code)

Max Activating Token Index: 951

Text #7

Max Range: 1.2563. Min Range: -1.2563

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1411332 (Python Code)

Max Activating Token Index: 599

Text #8

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.9834. Min Act: -0.0000

Data Index: 1619275 (Python Code)

Max Activating Token Index: 281

Text #9

Max Range: 1.2563. Min Range: -1.2563

Max Act: 1.0659. Min Act: -0.0000

Data Index: 1632513 (Python Code)

Max Activating Token Index: 899

Text #10

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.9900. Min Act: -0.0000

Data Index: 1425025 (Python Code)

Max Activating Token Index: 414

Text #11

Max Range: 1.2563. Min Range: -1.2563

Max Act: 1.0725. Min Act: -0.0000

Data Index: 1539020 (Python Code)

Max Activating Token Index: 212

Text #12

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1628549 (Python Code)

Max Activating Token Index: 23

Text #13

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.9443. Min Act: -0.0000

Data Index: 1606860 (Python Code)

Max Activating Token Index: 300

Text #14

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1585203 (Python Code)

Max Activating Token Index: 58

Text #15

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.9216. Min Act: -0.0000

Data Index: 1488595 (Python Code)

Max Activating Token Index: 299

Text #16

Max Range: 1.2563. Min Range: -1.2563

Max Act: 1.0044. Min Act: -0.0000

Data Index: 1481712 (Python Code)

Max Activating Token Index: 340

Text #17

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1459417 (Python Code)

Max Activating Token Index: 302

Text #18

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.7879. Min Act: -0.0000

Data Index: 1379521 (Python Code)

Max Activating Token Index: 210

Text #19

Max Range: 1.2563. Min Range: -1.2563

Max Act: 0.9130. Min Act: -0.0000

Data Index: 1486926 (Python Code)

Max Activating Token Index: 745