Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 288 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.0665. Min Range: -5.0665

Max Act: 5.0665. Min Act: -0.1700

Data Index: 1595672 (Python Code)

Max Activating Token Index: 24

Text #1

Max Range: 5.0665. Min Range: -5.0665

Max Act: 5.0665. Min Act: -0.1700

Data Index: 1637523 (Python Code)

Max Activating Token Index: 15

Text #2

Max Range: 5.0665. Min Range: -5.0665

Max Act: 5.0352. Min Act: -0.1700

Data Index: 1555200 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 5.0665. Min Range: -5.0665

Max Act: 5.0352. Min Act: -0.1700

Data Index: 1634888 (Python Code)

Max Activating Token Index: 15

Text #4

Max Range: 5.0665. Min Range: -5.0665

Max Act: 4.9727. Min Act: -0.1700

Data Index: 1368535 (Python Code)

Max Activating Token Index: 21

Text #5

Max Range: 5.0665. Min Range: -5.0665

Max Act: 5.0352. Min Act: -0.1700

Data Index: 1393010 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 5.0665. Min Range: -5.0665

Max Act: 4.9727. Min Act: -0.1700

Data Index: 1611859 (Python Code)

Max Activating Token Index: 21

Text #7

Max Range: 5.0665. Min Range: -5.0665

Max Act: 4.9727. Min Act: -0.1700

Data Index: 1648826 (Python Code)

Max Activating Token Index: 36

Text #8

Max Range: 5.0665. Min Range: -5.0665

Max Act: 4.8790. Min Act: -0.1700

Data Index: 1402301 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 5.0665. Min Range: -5.0665

Max Act: 4.9415. Min Act: -0.1700

Data Index: 1583561 (Python Code)

Max Activating Token Index: 925

Text #10

Max Range: 5.0665. Min Range: -5.0665

Max Act: 4.8790. Min Act: -0.1700

Data Index: 1583345 (Python Code)

Max Activating Token Index: 30

Text #11

Max Range: 5.0665. Min Range: -5.0665

Max Act: 4.8790. Min Act: -0.1700

Data Index: 1441349 (Python Code)

Max Activating Token Index: 68

Text #12

Max Range: 5.0665. Min Range: -5.0665

Max Act: 4.8790. Min Act: -0.1700

Data Index: 1408365 (Python Code)

Max Activating Token Index: 30

Text #13

Max Range: 5.0665. Min Range: -5.0665

Max Act: 4.8477. Min Act: -0.1700

Data Index: 1361591 (Python Code)

Max Activating Token Index: 333

Text #14

Max Range: 5.0665. Min Range: -5.0665

Max Act: 4.8477. Min Act: -0.1700

Data Index: 1574495 (Python Code)

Max Activating Token Index: 33

Text #15

Max Range: 5.0665. Min Range: -5.0665

Max Act: 4.8790. Min Act: -0.1700

Data Index: 1376717 (Python Code)

Max Activating Token Index: 792

Text #16

Max Range: 5.0665. Min Range: -5.0665

Max Act: 4.8165. Min Act: -0.1700

Data Index: 1555471 (Python Code)

Max Activating Token Index: 159

Text #17

Max Range: 5.0665. Min Range: -5.0665

Max Act: 4.8477. Min Act: -0.1700

Data Index: 1361555 (Python Code)

Max Activating Token Index: 787

Text #18

Max Range: 5.0665. Min Range: -5.0665

Max Act: 4.8165. Min Act: -0.1700

Data Index: 1620582 (Python Code)

Max Activating Token Index: 24

Text #19

Max Range: 5.0665. Min Range: -5.0665

Max Act: 4.8477. Min Act: -0.1700

Data Index: 1622985 (Python Code)

Max Activating Token Index: 8