Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 862 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.3528. Min Act: -0.1700

Data Index: 1376963 (Python Code)

Max Activating Token Index: 966

Text #1

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.3004. Min Act: -0.1700

Data Index: 1465786 (Python Code)

Max Activating Token Index: 283

Text #2

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.2702. Min Act: -0.1700

Data Index: 973944 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.2570. Min Act: -0.1700

Data Index: 1525190 (Python Code)

Max Activating Token Index: 791

Text #4

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.2849. Min Act: -0.1700

Data Index: 1376834 (Python Code)

Max Activating Token Index: 600

Text #5

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.1805. Min Act: -0.1700

Data Index: 687952 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.2480. Min Act: -0.1700

Data Index: 359923 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.2141. Min Act: -0.1700

Data Index: 971813 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.1864. Min Act: -0.1700

Data Index: 862714 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.1883. Min Act: -0.1700

Data Index: 1525398 (Python Code)

Max Activating Token Index: 454

Text #10

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.1785. Min Act: -0.1700

Data Index: 1449232 (Python Code)

Max Activating Token Index: 1012

Text #11

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.1437. Min Act: -0.1700

Data Index: 1432243 (Python Code)

Max Activating Token Index: 816

Text #12

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.1446. Min Act: -0.1700

Data Index: 748604 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.1811. Min Act: -0.1700

Data Index: 1462310 (Python Code)

Max Activating Token Index: 773

Text #14

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.2181. Min Act: -0.1700

Data Index: 1516181 (Python Code)

Max Activating Token Index: 806

Text #15

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.1602. Min Act: -0.1700

Data Index: 1432500 (Python Code)

Max Activating Token Index: 411

Text #16

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.1986. Min Act: -0.1700

Data Index: 881594 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.1113. Min Act: -0.1700

Data Index: 1253147 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.1424. Min Act: -0.1700

Data Index: 1551558 (Python Code)

Max Activating Token Index: 32

Text #19

Max Range: 3.3528. Min Range: -3.3528

Max Act: 3.1562. Min Act: -0.1700

Data Index: 1613368 (Python Code)

Max Activating Token Index: 22