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

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

Neuron 187 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1841. Min Act: -0.0003

Data Index: 47803 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1875. Min Act: -0.0003

Data Index: 1317442 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1757. Min Act: -0.0003

Data Index: 1008464 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1762. Min Act: -0.0003

Data Index: 282811 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1614. Min Act: -0.0003

Data Index: 444769 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1679. Min Act: -0.0003

Data Index: 46100 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1538. Min Act: -0.0003

Data Index: 1092269 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1698. Min Act: -0.0003

Data Index: 989129 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1619. Min Act: -0.0003

Data Index: 1456758 (Python Code)

Max Activating Token Index: 452

Text #9

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1666. Min Act: -0.0003

Data Index: 1124200 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1475. Min Act: -0.0003

Data Index: 956372 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1485. Min Act: -0.0003

Data Index: 1129456 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1485. Min Act: -0.0003

Data Index: 266402 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1470. Min Act: -0.0003

Data Index: 665264 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1515. Min Act: -0.0003

Data Index: 1211127 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1374. Min Act: -0.0003

Data Index: 1513891 (Python Code)

Max Activating Token Index: 84

Text #16

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1449. Min Act: -0.0003

Data Index: 1119785 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1446. Min Act: -0.0003

Data Index: 1172814 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1493. Min Act: -0.0003

Data Index: 1204125 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1375. Min Act: -0.0003

Data Index: 259803 (C4 (Web Text))

Max Activating Token Index: 72