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

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

Neuron 1844 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: 3.8858. Min Range: -3.8858

Max Act: 3.8858. Min Act: -0.1700

Data Index: 806328 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 3.8858. Min Range: -3.8858

Max Act: 3.8233. Min Act: -0.1700

Data Index: 441479 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 3.8858. Min Range: -3.8858

Max Act: 3.8233. Min Act: -0.1700

Data Index: 418659 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 3.8858. Min Range: -3.8858

Max Act: 3.8545. Min Act: -0.1700

Data Index: 538847 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 3.8858. Min Range: -3.8858

Max Act: 3.8233. Min Act: -0.1700

Data Index: 639373 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 3.8858. Min Range: -3.8858

Max Act: 3.8858. Min Act: -0.1700

Data Index: 1005267 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 3.8858. Min Range: -3.8858

Max Act: 3.8545. Min Act: -0.1700

Data Index: 312420 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 3.8858. Min Range: -3.8858

Max Act: 3.8233. Min Act: -0.1700

Data Index: 987393 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 3.8858. Min Range: -3.8858

Max Act: 3.8545. Min Act: -0.1700

Data Index: 978109 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 3.8858. Min Range: -3.8858

Max Act: 3.7920. Min Act: -0.1700

Data Index: 879823 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 3.8858. Min Range: -3.8858

Max Act: 3.8233. Min Act: -0.1700

Data Index: 375724 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 3.8858. Min Range: -3.8858

Max Act: 3.8233. Min Act: -0.1700

Data Index: 616078 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 3.8858. Min Range: -3.8858

Max Act: 3.7920. Min Act: -0.1700

Data Index: 1203051 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 3.8858. Min Range: -3.8858

Max Act: 3.7920. Min Act: -0.1700

Data Index: 90902 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 3.8858. Min Range: -3.8858

Max Act: 3.7920. Min Act: -0.1700

Data Index: 827241 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 3.8858. Min Range: -3.8858

Max Act: 3.8233. Min Act: -0.1700

Data Index: 404139 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 3.8858. Min Range: -3.8858

Max Act: 3.7920. Min Act: -0.1700

Data Index: 541816 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 3.8858. Min Range: -3.8858

Max Act: 3.7607. Min Act: -0.1700

Data Index: 497655 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 3.8858. Min Range: -3.8858

Max Act: 3.7607. Min Act: -0.1700

Data Index: 960241 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 3.8858. Min Range: -3.8858

Max Act: 3.7294. Min Act: -0.1700

Data Index: 592821 (C4 (Web Text))

Max Activating Token Index: 872