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

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

Neuron 1468 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: 4.2306. Min Range: -4.2306

Max Act: 4.2306. Min Act: -0.1698

Data Index: 1548743 (Python Code)

Max Activating Token Index: 336

Text #1

Max Range: 4.2306. Min Range: -4.2306

Max Act: 4.0430. Min Act: -0.1700

Data Index: 1619575 (Python Code)

Max Activating Token Index: 841

Text #2

Max Range: 4.2306. Min Range: -4.2306

Max Act: 3.9805. Min Act: -0.1700

Data Index: 1437873 (Python Code)

Max Activating Token Index: 34

Text #3

Max Range: 4.2306. Min Range: -4.2306

Max Act: 4.0118. Min Act: -0.1691

Data Index: 1646670 (Python Code)

Max Activating Token Index: 208

Text #4

Max Range: 4.2306. Min Range: -4.2306

Max Act: 3.9492. Min Act: -0.1700

Data Index: 101488 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 4.2306. Min Range: -4.2306

Max Act: 3.9492. Min Act: -0.1700

Data Index: 1537747 (Python Code)

Max Activating Token Index: 28

Text #6

Max Range: 4.2306. Min Range: -4.2306

Max Act: 3.9492. Min Act: -0.1700

Data Index: 1528649 (Python Code)

Max Activating Token Index: 280

Text #7

Max Range: 4.2306. Min Range: -4.2306

Max Act: 3.9180. Min Act: -0.1697

Data Index: 1498833 (Python Code)

Max Activating Token Index: 23

Text #8

Max Range: 4.2306. Min Range: -4.2306

Max Act: 3.9180. Min Act: -0.1700

Data Index: 1395703 (Python Code)

Max Activating Token Index: 132

Text #9

Max Range: 4.2306. Min Range: -4.2306

Max Act: 3.9180. Min Act: -0.1700

Data Index: 1618172 (Python Code)

Max Activating Token Index: 124

Text #10

Max Range: 4.2306. Min Range: -4.2306

Max Act: 3.8867. Min Act: -0.1699

Data Index: 1544279 (Python Code)

Max Activating Token Index: 726

Text #11

Max Range: 4.2306. Min Range: -4.2306

Max Act: 3.8867. Min Act: -0.1700

Data Index: 1463465 (Python Code)

Max Activating Token Index: 213

Text #12

Max Range: 4.2306. Min Range: -4.2306

Max Act: 3.8711. Min Act: -0.1700

Data Index: 72271 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 4.2306. Min Range: -4.2306

Max Act: 3.8711. Min Act: -0.1621

Data Index: 1394465 (Python Code)

Max Activating Token Index: 39

Text #14

Max Range: 4.2306. Min Range: -4.2306

Max Act: 3.8085. Min Act: -0.1700

Data Index: 726830 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 4.2306. Min Range: -4.2306

Max Act: 3.8398. Min Act: -0.1700

Data Index: 797455 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 4.2306. Min Range: -4.2306

Max Act: 3.8242. Min Act: -0.1700

Data Index: 1199552 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 4.2306. Min Range: -4.2306

Max Act: 3.8085. Min Act: -0.1700

Data Index: 928425 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 4.2306. Min Range: -4.2306

Max Act: 3.8085. Min Act: -0.1700

Data Index: 435671 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 4.2306. Min Range: -4.2306

Max Act: 3.7929. Min Act: -0.1700

Data Index: 1267024 (C4 (Web Text))

Max Activating Token Index: 70