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

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

Neuron 1586 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: 3.0475. Min Range: -3.0475

Max Act: 3.0159. Min Act: -0.1700

Data Index: 769643 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.9843. Min Act: -0.1700

Data Index: 861864 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 3.0475. Min Range: -3.0475

Max Act: 3.0475. Min Act: -0.1700

Data Index: 252038 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 3.0475. Min Range: -3.0475

Max Act: 3.0159. Min Act: -0.1700

Data Index: 1138679 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.9368. Min Act: -0.1700

Data Index: 781217 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.9685. Min Act: -0.1700

Data Index: 465596 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.9685. Min Act: -0.1700

Data Index: 479952 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.9526. Min Act: -0.1700

Data Index: 1253650 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.9526. Min Act: -0.1700

Data Index: 167392 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.9210. Min Act: -0.1700

Data Index: 609486 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.9210. Min Act: -0.1700

Data Index: 620707 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8575. Min Act: -0.1700

Data Index: 1275900 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8892. Min Act: -0.1700

Data Index: 177475 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8575. Min Act: -0.1700

Data Index: 415009 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8257. Min Act: -0.1700

Data Index: 395115 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8257. Min Act: -0.1700

Data Index: 1282123 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8098. Min Act: -0.1700

Data Index: 885337 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8416. Min Act: -0.1700

Data Index: 914609 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8416. Min Act: -0.1700

Data Index: 675450 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 3.0475. Min Range: -3.0475

Max Act: 2.8257. Min Act: -0.1700

Data Index: 800466 (C4 (Web Text))

Max Activating Token Index: 875