Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 9 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0913. Min Act: -0.1700

Data Index: 476840 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0756. Min Act: -0.1700

Data Index: 1172691 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0913. Min Act: -0.1700

Data Index: 1532774 (Python Code)

Max Activating Token Index: 472

Text #3

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0913. Min Act: -0.1700

Data Index: 787365 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0913. Min Act: -0.1700

Data Index: 440456 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0756. Min Act: -0.1700

Data Index: 1418128 (Python Code)

Max Activating Token Index: 544

Text #6

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0598. Min Act: -0.1700

Data Index: 1520261 (Python Code)

Max Activating Token Index: 463

Text #7

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0756. Min Act: -0.1700

Data Index: 1579635 (Python Code)

Max Activating Token Index: 463

Text #8

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0598. Min Act: -0.1700

Data Index: 22015 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0598. Min Act: -0.1700

Data Index: 1532451 (Python Code)

Max Activating Token Index: 174

Text #10

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0440. Min Act: -0.1700

Data Index: 1555867 (Python Code)

Max Activating Token Index: 232

Text #11

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0282. Min Act: -0.1700

Data Index: 1488626 (Python Code)

Max Activating Token Index: 597

Text #12

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0440. Min Act: -0.1700

Data Index: 712340 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0440. Min Act: -0.1700

Data Index: 1397925 (Python Code)

Max Activating Token Index: 551

Text #14

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0440. Min Act: -0.1700

Data Index: 1609712 (Python Code)

Max Activating Token Index: 624

Text #15

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0440. Min Act: -0.1700

Data Index: 1427234 (Python Code)

Max Activating Token Index: 407

Text #16

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0440. Min Act: -0.1700

Data Index: 1484992 (Python Code)

Max Activating Token Index: 171

Text #17

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0282. Min Act: -0.1700

Data Index: 1487309 (Python Code)

Max Activating Token Index: 622

Text #18

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0282. Min Act: -0.1700

Data Index: 1570447 (Python Code)

Max Activating Token Index: 547

Text #19

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0282. Min Act: -0.1700

Data Index: 1415387 (Python Code)

Max Activating Token Index: 544