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

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

Neuron 450 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: 5.0264. Min Range: -5.0264

Max Act: 4.9951. Min Act: -0.1700

Data Index: 480623 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 5.0264. Min Range: -5.0264

Max Act: 4.9639. Min Act: -0.1700

Data Index: 30911 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 5.0264. Min Range: -5.0264

Max Act: 5.0264. Min Act: -0.1700

Data Index: 1101930 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 5.0264. Min Range: -5.0264

Max Act: 4.9014. Min Act: -0.1700

Data Index: 957943 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 5.0264. Min Range: -5.0264

Max Act: 4.9014. Min Act: -0.1700

Data Index: 341440 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 5.0264. Min Range: -5.0264

Max Act: 4.8389. Min Act: -0.1700

Data Index: 1264943 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 5.0264. Min Range: -5.0264

Max Act: 4.8389. Min Act: -0.1700

Data Index: 137469 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 5.0264. Min Range: -5.0264

Max Act: 4.7764. Min Act: -0.1700

Data Index: 910720 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 5.0264. Min Range: -5.0264

Max Act: 4.8076. Min Act: -0.1700

Data Index: 661292 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 5.0264. Min Range: -5.0264

Max Act: 4.7764. Min Act: -0.1700

Data Index: 969298 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 5.0264. Min Range: -5.0264

Max Act: 4.7764. Min Act: -0.1699

Data Index: 533625 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 5.0264. Min Range: -5.0264

Max Act: 4.8076. Min Act: -0.1700

Data Index: 267822 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 5.0264. Min Range: -5.0264

Max Act: 4.7764. Min Act: -0.1700

Data Index: 1295296 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 5.0264. Min Range: -5.0264

Max Act: 4.7764. Min Act: -0.1700

Data Index: 659193 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 5.0264. Min Range: -5.0264

Max Act: 4.7764. Min Act: -0.1700

Data Index: 985250 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 5.0264. Min Range: -5.0264

Max Act: 4.7451. Min Act: -0.1700

Data Index: 206559 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 5.0264. Min Range: -5.0264

Max Act: 4.7451. Min Act: -0.1700

Data Index: 1057748 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 5.0264. Min Range: -5.0264

Max Act: 4.7139. Min Act: -0.1700

Data Index: 943339 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 5.0264. Min Range: -5.0264

Max Act: 4.7139. Min Act: -0.1700

Data Index: 878439 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 5.0264. Min Range: -5.0264

Max Act: 4.7764. Min Act: -0.1700

Data Index: 902226 (C4 (Web Text))

Max Activating Token Index: 114