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

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

Neuron 638 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.1864. Min Act: -0.1700

Data Index: 429362 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.1864. Min Act: -0.1700

Data Index: 612336 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.1707. Min Act: -0.1700

Data Index: 167058 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.1076. Min Act: -0.1700

Data Index: 108305 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.1076. Min Act: -0.1700

Data Index: 1289278 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.1549. Min Act: -0.1700

Data Index: 627804 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.1234. Min Act: -0.1700

Data Index: 261935 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.0919. Min Act: -0.1700

Data Index: 835519 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.0761. Min Act: -0.1700

Data Index: 431062 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.0761. Min Act: -0.1700

Data Index: 629848 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.0919. Min Act: -0.1700

Data Index: 80810 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.0761. Min Act: -0.1700

Data Index: 1359604 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.0761. Min Act: -0.1700

Data Index: 1066171 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.0761. Min Act: -0.1700

Data Index: 688106 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.0603. Min Act: -0.1700

Data Index: 496225 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.0919. Min Act: -0.1700

Data Index: 229791 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.0603. Min Act: -0.1700

Data Index: 1083050 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.0603. Min Act: -0.1700

Data Index: 890627 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.0603. Min Act: -0.1700

Data Index: 551404 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.0287. Min Act: -0.1700

Data Index: 654583 (C4 (Web Text))

Max Activating Token Index: 631