Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1626 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.6784. Min Act: -0.1700

Data Index: 1606137 (Python Code)

Max Activating Token Index: 380

Text #1

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.6471. Min Act: -0.1700

Data Index: 1432009 (Python Code)

Max Activating Token Index: 518

Text #2

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.6315. Min Act: -0.1700

Data Index: 1483665 (Python Code)

Max Activating Token Index: 772

Text #3

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5845. Min Act: -0.1700

Data Index: 1420905 (Python Code)

Max Activating Token Index: 70

Text #4

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5689. Min Act: -0.1700

Data Index: 1595407 (Python Code)

Max Activating Token Index: 124

Text #5

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5845. Min Act: -0.1700

Data Index: 1544178 (Python Code)

Max Activating Token Index: 103

Text #6

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5375. Min Act: -0.1700

Data Index: 1375726 (Python Code)

Max Activating Token Index: 855

Text #7

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5375. Min Act: -0.1700

Data Index: 1360297 (Python Code)

Max Activating Token Index: 172

Text #8

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5375. Min Act: -0.1700

Data Index: 1395281 (Python Code)

Max Activating Token Index: 645

Text #9

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5219. Min Act: -0.1700

Data Index: 1614177 (Python Code)

Max Activating Token Index: 195

Text #10

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5375. Min Act: -0.1700

Data Index: 1429423 (Python Code)

Max Activating Token Index: 667

Text #11

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.4905. Min Act: -0.1700

Data Index: 1628081 (Python Code)

Max Activating Token Index: 592

Text #12

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5062. Min Act: -0.1700

Data Index: 1482524 (Python Code)

Max Activating Token Index: 267

Text #13

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5062. Min Act: -0.1700

Data Index: 1520989 (Python Code)

Max Activating Token Index: 262

Text #14

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5062. Min Act: -0.1700

Data Index: 1648693 (Python Code)

Max Activating Token Index: 719

Text #15

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.4905. Min Act: -0.1700

Data Index: 1366665 (Python Code)

Max Activating Token Index: 779

Text #16

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.4749. Min Act: -0.1700

Data Index: 1647016 (Python Code)

Max Activating Token Index: 272

Text #17

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.5219. Min Act: -0.1700

Data Index: 1505582 (Python Code)

Max Activating Token Index: 407

Text #18

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.4749. Min Act: -0.1700

Data Index: 1458342 (Python Code)

Max Activating Token Index: 183

Text #19

Max Range: 3.6784. Min Range: -3.6784

Max Act: 3.4592. Min Act: -0.1700

Data Index: 1514803 (Python Code)

Max Activating Token Index: 557