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

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

Neuron 175 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0123. Min Range: -5.0123

Max Act: 5.0123. Min Act: -0.1700

Data Index: 536839 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.8561. Min Act: -0.1700

Data Index: 1411905 (Python Code)

Max Activating Token Index: 475

Text #2

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.7936. Min Act: -0.1700

Data Index: 442617 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.7311. Min Act: -0.1700

Data Index: 1457031 (Python Code)

Max Activating Token Index: 216

Text #4

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.7623. Min Act: -0.1700

Data Index: 771041 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.6686. Min Act: -0.1700

Data Index: 397215 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.6373. Min Act: -0.1700

Data Index: 33914 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.6061. Min Act: -0.1700

Data Index: 812960 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.5436. Min Act: -0.1700

Data Index: 711967 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.5748. Min Act: -0.1700

Data Index: 80491 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.5748. Min Act: -0.1700

Data Index: 1532932 (Python Code)

Max Activating Token Index: 120

Text #11

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.5123. Min Act: -0.1700

Data Index: 1541869 (Python Code)

Max Activating Token Index: 574

Text #12

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.5748. Min Act: -0.1700

Data Index: 403215 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.5436. Min Act: -0.1700

Data Index: 501991 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.5436. Min Act: -0.1700

Data Index: 1287691 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.5123. Min Act: -0.1700

Data Index: 1639986 (Python Code)

Max Activating Token Index: 456

Text #16

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.5436. Min Act: -0.1700

Data Index: 1599300 (Python Code)

Max Activating Token Index: 250

Text #17

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.5436. Min Act: -0.1700

Data Index: 527310 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.5123. Min Act: -0.1700

Data Index: 220367 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 5.0123. Min Range: -5.0123

Max Act: 4.5436. Min Act: -0.1700

Data Index: 1257145 (C4 (Web Text))

Max Activating Token Index: 615