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

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

Neuron 267 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: 4.8356. Min Range: -4.8356

Max Act: 4.8356. Min Act: -0.1700

Data Index: 201544 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 4.8356. Min Range: -4.8356

Max Act: 4.7887. Min Act: -0.1700

Data Index: 637591 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 4.8356. Min Range: -4.8356

Max Act: 4.7575. Min Act: -0.1698

Data Index: 671365 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 4.8356. Min Range: -4.8356

Max Act: 4.7106. Min Act: -0.1699

Data Index: 1195801 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 4.8356. Min Range: -4.8356

Max Act: 4.6637. Min Act: -0.1700

Data Index: 384860 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 4.8356. Min Range: -4.8356

Max Act: 4.6168. Min Act: -0.1700

Data Index: 1189224 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 4.8356. Min Range: -4.8356

Max Act: 4.6325. Min Act: -0.1700

Data Index: 981684 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 4.8356. Min Range: -4.8356

Max Act: 4.6481. Min Act: -0.1699

Data Index: 945798 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 4.8356. Min Range: -4.8356

Max Act: 4.6325. Min Act: -0.1700

Data Index: 25631 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 4.8356. Min Range: -4.8356

Max Act: 4.6012. Min Act: -0.1700

Data Index: 539774 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 4.8356. Min Range: -4.8356

Max Act: 4.6325. Min Act: -0.1700

Data Index: 77429 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 4.8356. Min Range: -4.8356

Max Act: 4.6168. Min Act: -0.1700

Data Index: 54563 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 4.8356. Min Range: -4.8356

Max Act: 4.5700. Min Act: -0.1700

Data Index: 27571 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 4.8356. Min Range: -4.8356

Max Act: 4.5387. Min Act: -0.1700

Data Index: 742504 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 4.8356. Min Range: -4.8356

Max Act: 4.5543. Min Act: -0.1700

Data Index: 5101 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 4.8356. Min Range: -4.8356

Max Act: 4.5231. Min Act: -0.1700

Data Index: 460588 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 4.8356. Min Range: -4.8356

Max Act: 4.4918. Min Act: -0.1700

Data Index: 350334 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 4.8356. Min Range: -4.8356

Max Act: 4.4918. Min Act: -0.1700

Data Index: 276731 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 4.8356. Min Range: -4.8356

Max Act: 4.4762. Min Act: -0.1700

Data Index: 702966 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 4.8356. Min Range: -4.8356

Max Act: 4.4450. Min Act: -0.1700

Data Index: 861356 (C4 (Web Text))

Max Activating Token Index: 36