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

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

Neuron 77 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.9762. Min Act: -0.1700

Data Index: 721199 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.9449. Min Act: -0.1700

Data Index: 222536 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.9449. Min Act: -0.1700

Data Index: 1199381 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.8824. Min Act: -0.1700

Data Index: 1097186 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.8824. Min Act: -0.1699

Data Index: 3753 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.8824. Min Act: -0.1700

Data Index: 968503 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.8511. Min Act: -0.1700

Data Index: 722637 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.8198. Min Act: -0.1700

Data Index: 33396 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.7886. Min Act: -0.1700

Data Index: 424338 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.7416. Min Act: -0.1700

Data Index: 432802 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.7573. Min Act: -0.1700

Data Index: 120224 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.7573. Min Act: -0.1700

Data Index: 653772 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.6790. Min Act: -0.1700

Data Index: 713622 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.6164. Min Act: -0.1700

Data Index: 99502 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.6164. Min Act: -0.1700

Data Index: 210911 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.6164. Min Act: -0.1700

Data Index: 1340986 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.6008. Min Act: -0.1700

Data Index: 150478 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.5381. Min Act: -0.1700

Data Index: 954206 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.5381. Min Act: -0.1700

Data Index: 66969 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.5538. Min Act: -0.1700

Data Index: 580710 (C4 (Web Text))

Max Activating Token Index: 673