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

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

Neuron 29 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: 3.8517. Min Range: -3.8517

Max Act: 3.8517. Min Act: -0.1700

Data Index: 475655 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.7891. Min Act: -0.1700

Data Index: 1230909 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6952. Min Act: -0.1700

Data Index: 498736 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6170. Min Act: -0.1700

Data Index: 900625 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6326. Min Act: -0.1700

Data Index: 1312614 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.6013. Min Act: -0.1700

Data Index: 1295374 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.5700. Min Act: -0.1700

Data Index: 961968 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.5543. Min Act: -0.1700

Data Index: 1002089 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.5543. Min Act: -0.1700

Data Index: 755188 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.5543. Min Act: -0.1700

Data Index: 213467 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.5387. Min Act: -0.1700

Data Index: 1248431 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.5387. Min Act: -0.1700

Data Index: 1228873 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.5073. Min Act: -0.1700

Data Index: 1287772 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.4760. Min Act: -0.1700

Data Index: 776541 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.4917. Min Act: -0.1700

Data Index: 801886 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.4760. Min Act: -0.1700

Data Index: 1248322 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.4760. Min Act: -0.1700

Data Index: 842591 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.4760. Min Act: -0.1700

Data Index: 931293 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.4760. Min Act: -0.1700

Data Index: 478504 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 3.8517. Min Range: -3.8517

Max Act: 3.4447. Min Act: -0.1700

Data Index: 283549 (C4 (Web Text))

Max Activating Token Index: 956