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

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

Neuron 1862 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.4649. Min Act: -0.1700

Data Index: 369278 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.4649. Min Act: -0.1700

Data Index: 516817 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.4649. Min Act: -0.1700

Data Index: 415178 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.4492. Min Act: -0.1700

Data Index: 570619 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.4649. Min Act: -0.1700

Data Index: 1175172 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.4335. Min Act: -0.1700

Data Index: 1217327 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.4492. Min Act: -0.1700

Data Index: 796946 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.4022. Min Act: -0.1700

Data Index: 180399 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.4178. Min Act: -0.1700

Data Index: 848821 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.4178. Min Act: -0.1700

Data Index: 157371 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.3708. Min Act: -0.1700

Data Index: 1188665 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.3865. Min Act: -0.1700

Data Index: 567568 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.4022. Min Act: -0.1700

Data Index: 883386 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.4022. Min Act: -0.1700

Data Index: 519222 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.3708. Min Act: -0.1700

Data Index: 978246 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.4022. Min Act: -0.1700

Data Index: 1306949 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.3865. Min Act: -0.1700

Data Index: 715165 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.3865. Min Act: -0.1700

Data Index: 435287 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.3865. Min Act: -0.1700

Data Index: 258315 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 3.4649. Min Range: -3.4649

Max Act: 3.3708. Min Act: -0.1700

Data Index: 822859 (C4 (Web Text))

Max Activating Token Index: 949