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

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

Neuron 857 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.5800. Min Act: -0.1700

Data Index: 596556 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.2664. Min Act: -0.1700

Data Index: 483869 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.2664. Min Act: -0.1700

Data Index: 404084 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.2349. Min Act: -0.1700

Data Index: 21686 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.3292. Min Act: -0.1700

Data Index: 402342 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.2035. Min Act: -0.1700

Data Index: 344419 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.2349. Min Act: -0.1700

Data Index: 645729 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.2349. Min Act: -0.1700

Data Index: 299992 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.2035. Min Act: -0.1700

Data Index: 939496 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.2349. Min Act: -0.1700

Data Index: 990640 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.2349. Min Act: -0.1700

Data Index: 1051746 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.1405. Min Act: -0.1700

Data Index: 1354064 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.1720. Min Act: -0.1700

Data Index: 724632 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.2035. Min Act: -0.1700

Data Index: 638608 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.2035. Min Act: -0.1700

Data Index: 53902 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.1720. Min Act: -0.1700

Data Index: 479844 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.0932. Min Act: -0.1700

Data Index: 1014275 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.1720. Min Act: -0.1700

Data Index: 458131 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.1720. Min Act: -0.1700

Data Index: 830225 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.1405. Min Act: -0.1700

Data Index: 109805 (C4 (Web Text))

Max Activating Token Index: 632