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

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

Neuron 1799 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.2698. Min Act: -0.1700

Data Index: 95105 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.2698. Min Act: -0.1700

Data Index: 795854 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.2541. Min Act: -0.1700

Data Index: 1534731 (Python Code)

Max Activating Token Index: 748

Text #3

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.1755. Min Act: -0.1700

Data Index: 1362717 (Python Code)

Max Activating Token Index: 730

Text #4

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.1597. Min Act: -0.1700

Data Index: 1545225 (Python Code)

Max Activating Token Index: 555

Text #5

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.1755. Min Act: -0.1700

Data Index: 1621162 (Python Code)

Max Activating Token Index: 255

Text #6

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.0967. Min Act: -0.1700

Data Index: 1562867 (Python Code)

Max Activating Token Index: 697

Text #7

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.1282. Min Act: -0.1700

Data Index: 1597617 (Python Code)

Max Activating Token Index: 761

Text #8

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.1282. Min Act: -0.1700

Data Index: 1319502 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.1125. Min Act: -0.1700

Data Index: 1099501 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.0967. Min Act: -0.1700

Data Index: 892112 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.0967. Min Act: -0.1700

Data Index: 1637935 (Python Code)

Max Activating Token Index: 251

Text #12

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.0651. Min Act: -0.1700

Data Index: 1531275 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.0809. Min Act: -0.1700

Data Index: 576764 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.0967. Min Act: -0.1700

Data Index: 132933 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.0809. Min Act: -0.1700

Data Index: 524620 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.0809. Min Act: -0.1700

Data Index: 48183 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.0809. Min Act: -0.1700

Data Index: 407201 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.0651. Min Act: -0.1700

Data Index: 726156 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 3.2698. Min Range: -3.2698

Max Act: 3.0651. Min Act: -0.1700

Data Index: 1232008 (C4 (Web Text))

Max Activating Token Index: 166