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

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

Neuron 668 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: 5.6589. Min Range: -5.6589

Max Act: 5.6589. Min Act: -0.1700

Data Index: 80009 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 5.6589. Min Range: -5.6589

Max Act: 5.5027. Min Act: -0.1700

Data Index: 721377 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 5.6589. Min Range: -5.6589

Max Act: 5.5027. Min Act: -0.1700

Data Index: 1055842 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 5.6589. Min Range: -5.6589

Max Act: 5.5027. Min Act: -0.1700

Data Index: 152612 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 5.6589. Min Range: -5.6589

Max Act: 5.4402. Min Act: -0.1700

Data Index: 118377 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 5.6589. Min Range: -5.6589

Max Act: 5.4089. Min Act: -0.1700

Data Index: 872256 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 5.6589. Min Range: -5.6589

Max Act: 5.4714. Min Act: -0.1700

Data Index: 700897 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 5.6589. Min Range: -5.6589

Max Act: 5.4714. Min Act: -0.1700

Data Index: 385618 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 5.6589. Min Range: -5.6589

Max Act: 5.4089. Min Act: -0.1700

Data Index: 677763 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 5.6589. Min Range: -5.6589

Max Act: 5.4089. Min Act: -0.1700

Data Index: 430981 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 5.6589. Min Range: -5.6589

Max Act: 5.4089. Min Act: -0.1700

Data Index: 1346465 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 5.6589. Min Range: -5.6589

Max Act: 5.3777. Min Act: -0.1700

Data Index: 285318 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 5.6589. Min Range: -5.6589

Max Act: 5.3464. Min Act: -0.1700

Data Index: 1358642 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 5.6589. Min Range: -5.6589

Max Act: 5.3777. Min Act: -0.1700

Data Index: 665703 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 5.6589. Min Range: -5.6589

Max Act: 5.3464. Min Act: -0.1700

Data Index: 809445 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 5.6589. Min Range: -5.6589

Max Act: 5.3152. Min Act: -0.1700

Data Index: 976997 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 5.6589. Min Range: -5.6589

Max Act: 5.2527. Min Act: -0.1700

Data Index: 680909 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 5.6589. Min Range: -5.6589

Max Act: 5.2839. Min Act: -0.1700

Data Index: 1227142 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 5.6589. Min Range: -5.6589

Max Act: 5.3464. Min Act: -0.1700

Data Index: 1135350 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 5.6589. Min Range: -5.6589

Max Act: 5.2839. Min Act: -0.1700

Data Index: 776425 (C4 (Web Text))

Max Activating Token Index: 23