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

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

Neuron 390 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1590. Min Range: -5.1590

Max Act: 5.1277. Min Act: -0.1700

Data Index: 980979 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 5.1590. Min Range: -5.1590

Max Act: 5.0652. Min Act: -0.1700

Data Index: 789131 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 5.1590. Min Range: -5.1590

Max Act: 5.1590. Min Act: -0.1700

Data Index: 429445 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 5.1590. Min Range: -5.1590

Max Act: 5.0339. Min Act: -0.1700

Data Index: 1100453 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 5.1590. Min Range: -5.1590

Max Act: 5.0027. Min Act: -0.1700

Data Index: 466005 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 5.1590. Min Range: -5.1590

Max Act: 5.0027. Min Act: -0.1700

Data Index: 1277890 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 5.1590. Min Range: -5.1590

Max Act: 5.0339. Min Act: -0.1700

Data Index: 328877 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 5.1590. Min Range: -5.1590

Max Act: 4.9714. Min Act: -0.1700

Data Index: 283692 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 5.1590. Min Range: -5.1590

Max Act: 4.9714. Min Act: -0.1700

Data Index: 227715 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 5.1590. Min Range: -5.1590

Max Act: 4.9089. Min Act: -0.1700

Data Index: 1351333 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 5.1590. Min Range: -5.1590

Max Act: 4.9402. Min Act: -0.1700

Data Index: 190842 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 5.1590. Min Range: -5.1590

Max Act: 4.8464. Min Act: -0.1700

Data Index: 995043 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 5.1590. Min Range: -5.1590

Max Act: 4.9089. Min Act: -0.1700

Data Index: 588949 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 5.1590. Min Range: -5.1590

Max Act: 4.9089. Min Act: -0.1700

Data Index: 532170 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 5.1590. Min Range: -5.1590

Max Act: 4.9402. Min Act: -0.1700

Data Index: 290132 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 5.1590. Min Range: -5.1590

Max Act: 4.8464. Min Act: -0.1700

Data Index: 273450 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 5.1590. Min Range: -5.1590

Max Act: 4.8777. Min Act: -0.1700

Data Index: 521263 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 5.1590. Min Range: -5.1590

Max Act: 4.8464. Min Act: -0.1700

Data Index: 626467 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 5.1590. Min Range: -5.1590

Max Act: 4.8777. Min Act: -0.1700

Data Index: 670378 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 5.1590. Min Range: -5.1590

Max Act: 4.9402. Min Act: -0.1700

Data Index: 200940 (C4 (Web Text))

Max Activating Token Index: 767