Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 78 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.6984. Min Act: -0.1700

Data Index: 564221 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.5734. Min Act: -0.1700

Data Index: 617425 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.5734. Min Act: -0.1700

Data Index: 943055 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.6047. Min Act: -0.1700

Data Index: 1243240 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.5109. Min Act: -0.1700

Data Index: 663232 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.5422. Min Act: -0.1700

Data Index: 740487 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.4797. Min Act: -0.1700

Data Index: 381871 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.4797. Min Act: -0.1700

Data Index: 338102 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.4797. Min Act: -0.1700

Data Index: 149069 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.4797. Min Act: -0.1700

Data Index: 555445 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.4484. Min Act: -0.1700

Data Index: 973143 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.4484. Min Act: -0.1700

Data Index: 970291 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.4484. Min Act: -0.1700

Data Index: 920524 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.4172. Min Act: -0.1700

Data Index: 1104802 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.5109. Min Act: -0.1700

Data Index: 672136 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.4172. Min Act: -0.1700

Data Index: 42418 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.4797. Min Act: -0.1700

Data Index: 832742 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.4172. Min Act: -0.1700

Data Index: 722381 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.4172. Min Act: -0.1700

Data Index: 358862 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 5.6984. Min Range: -5.6984

Max Act: 5.4484. Min Act: -0.1700

Data Index: 209716 (C4 (Web Text))

Max Activating Token Index: 34