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

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

Neuron 1769 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.6638. Min Act: -0.1700

Data Index: 1108849 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.6638. Min Act: -0.1700

Data Index: 900615 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.6011. Min Act: -0.1700

Data Index: 718097 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.6011. Min Act: -0.1700

Data Index: 844265 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.6011. Min Act: -0.1700

Data Index: 77749 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.5698. Min Act: -0.1700

Data Index: 1021572 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.5698. Min Act: -0.1700

Data Index: 737270 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.5542. Min Act: -0.1700

Data Index: 463704 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.5698. Min Act: -0.1700

Data Index: 1329446 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.5698. Min Act: -0.1700

Data Index: 1317709 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.5542. Min Act: -0.1700

Data Index: 525791 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.5542. Min Act: -0.1700

Data Index: 1244098 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.5542. Min Act: -0.1700

Data Index: 345301 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.5542. Min Act: -0.1700

Data Index: 497621 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.5542. Min Act: -0.1700

Data Index: 670195 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.5385. Min Act: -0.1700

Data Index: 966751 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.5072. Min Act: -0.1700

Data Index: 623593 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.5542. Min Act: -0.1700

Data Index: 118020 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.5228. Min Act: -0.1700

Data Index: 1180258 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 3.6638. Min Range: -3.6638

Max Act: 3.5228. Min Act: -0.1700

Data Index: 1186602 (C4 (Web Text))

Max Activating Token Index: 493