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

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

Neuron 668 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0019. Min Range: -5.0019

Max Act: 5.0019. Min Act: -0.1700

Data Index: 787345 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.8144. Min Act: -0.1700

Data Index: 773663 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.7207. Min Act: -0.1700

Data Index: 911638 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.6894. Min Act: -0.1700

Data Index: 1025397 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.6894. Min Act: -0.1700

Data Index: 1149245 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.6582. Min Act: -0.1700

Data Index: 415150 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.6426. Min Act: -0.1700

Data Index: 965797 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.6426. Min Act: -0.1700

Data Index: 355144 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.5644. Min Act: -0.1700

Data Index: 618298 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.5488. Min Act: -0.1700

Data Index: 660360 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.5488. Min Act: -0.1700

Data Index: 1254777 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.5488. Min Act: -0.1700

Data Index: 267188 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.5488. Min Act: -0.1700

Data Index: 841436 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.5019. Min Act: -0.1700

Data Index: 294959 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.5176. Min Act: -0.1700

Data Index: 320403 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.4707. Min Act: -0.1700

Data Index: 923178 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.5019. Min Act: -0.1700

Data Index: 302309 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.4707. Min Act: -0.1700

Data Index: 704214 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.4707. Min Act: -0.1700

Data Index: 734666 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 5.0019. Min Range: -5.0019

Max Act: 4.4394. Min Act: -0.1700

Data Index: 83116 (C4 (Web Text))

Max Activating Token Index: 396