Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 973 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.7483. Min Act: -0.1700

Data Index: 1404501 (Python Code)

Max Activating Token Index: 294

Text #1

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.3724. Min Act: -0.1698

Data Index: 1404241 (Python Code)

Max Activating Token Index: 431

Text #2

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.4038. Min Act: -0.1653

Data Index: 1529818 (Python Code)

Max Activating Token Index: 189

Text #3

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.4038. Min Act: -0.1700

Data Index: 1630089 (Python Code)

Max Activating Token Index: 448

Text #4

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.3724. Min Act: -0.1697

Data Index: 1453228 (Python Code)

Max Activating Token Index: 964

Text #5

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.3724. Min Act: -0.1700

Data Index: 1479834 (Python Code)

Max Activating Token Index: 415

Text #6

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.3410. Min Act: -0.1700

Data Index: 1400094 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.3410. Min Act: -0.1700

Data Index: 1490946 (Python Code)

Max Activating Token Index: 858

Text #8

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.2782. Min Act: -0.1688

Data Index: 1365433 (Python Code)

Max Activating Token Index: 807

Text #9

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.2782. Min Act: -0.1700

Data Index: 1364518 (Python Code)

Max Activating Token Index: 425

Text #10

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.2782. Min Act: -0.1700

Data Index: 1634913 (Python Code)

Max Activating Token Index: 847

Text #11

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.2782. Min Act: -0.1699

Data Index: 1467635 (Python Code)

Max Activating Token Index: 825

Text #12

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.2782. Min Act: -0.1699

Data Index: 1382682 (Python Code)

Max Activating Token Index: 944

Text #13

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.2782. Min Act: -0.1699

Data Index: 1449355 (Python Code)

Max Activating Token Index: 961

Text #14

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.2468. Min Act: -0.1699

Data Index: 1628218 (Python Code)

Max Activating Token Index: 451

Text #15

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.2468. Min Act: -0.1700

Data Index: 1477534 (Python Code)

Max Activating Token Index: 510

Text #16

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.2468. Min Act: -0.1700

Data Index: 148466 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.2468. Min Act: -0.1700

Data Index: 1442622 (Python Code)

Max Activating Token Index: 841

Text #18

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.2153. Min Act: -0.1700

Data Index: 1589527 (Python Code)

Max Activating Token Index: 812

Text #19

Max Range: 3.7483. Min Range: -3.7483

Max Act: 3.1839. Min Act: -0.1700

Data Index: 1609882 (Python Code)

Max Activating Token Index: 742