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

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

Neuron 473 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: 3.7018. Min Range: -3.7018

Max Act: 3.7018. Min Act: -0.1700

Data Index: 984413 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 3.7018. Min Range: -3.7018

Max Act: 3.4199. Min Act: -0.1700

Data Index: 1310527 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 3.7018. Min Range: -3.7018

Max Act: 3.4199. Min Act: -0.1700

Data Index: 924678 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 3.7018. Min Range: -3.7018

Max Act: 3.4199. Min Act: -0.1700

Data Index: 504878 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 3.7018. Min Range: -3.7018

Max Act: 3.4199. Min Act: -0.1700

Data Index: 891391 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 3.7018. Min Range: -3.7018

Max Act: 3.3885. Min Act: -0.1700

Data Index: 1137024 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 3.7018. Min Range: -3.7018

Max Act: 3.4512. Min Act: -0.1700

Data Index: 1357533 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 3.7018. Min Range: -3.7018

Max Act: 3.4042. Min Act: -0.1700

Data Index: 643113 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 3.7018. Min Range: -3.7018

Max Act: 3.3885. Min Act: -0.1700

Data Index: 342558 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 3.7018. Min Range: -3.7018

Max Act: 3.3885. Min Act: -0.1700

Data Index: 738528 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 3.7018. Min Range: -3.7018

Max Act: 3.3728. Min Act: -0.1700

Data Index: 1372785 (Python Code)

Max Activating Token Index: 455

Text #11

Max Range: 3.7018. Min Range: -3.7018

Max Act: 3.3571. Min Act: -0.1700

Data Index: 986520 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 3.7018. Min Range: -3.7018

Max Act: 3.3257. Min Act: -0.1700

Data Index: 49206 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 3.7018. Min Range: -3.7018

Max Act: 3.3571. Min Act: -0.1700

Data Index: 266326 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 3.7018. Min Range: -3.7018

Max Act: 3.2943. Min Act: -0.1700

Data Index: 201875 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 3.7018. Min Range: -3.7018

Max Act: 3.3100. Min Act: -0.1700

Data Index: 160321 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 3.7018. Min Range: -3.7018

Max Act: 3.3100. Min Act: -0.1700

Data Index: 651922 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 3.7018. Min Range: -3.7018

Max Act: 3.3257. Min Act: -0.1700

Data Index: 334651 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 3.7018. Min Range: -3.7018

Max Act: 3.3100. Min Act: -0.1700

Data Index: 319457 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 3.7018. Min Range: -3.7018

Max Act: 3.3100. Min Act: -0.1700

Data Index: 1014274 (C4 (Web Text))

Max Activating Token Index: 7