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

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

Neuron 1798 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: 3.0846. Min Range: -3.0846

Max Act: 3.0846. Min Act: -0.1700

Data Index: 840606 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 3.0846. Min Range: -3.0846

Max Act: 3.0846. Min Act: -0.1700

Data Index: 823831 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9898. Min Act: -0.1700

Data Index: 708605 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 3.0846. Min Range: -3.0846

Max Act: 3.0372. Min Act: -0.1700

Data Index: 856194 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 3.0846. Min Range: -3.0846

Max Act: 3.0214. Min Act: -0.1700

Data Index: 969269 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 3.0846. Min Range: -3.0846

Max Act: 3.0214. Min Act: -0.1700

Data Index: 740350 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 3.0846. Min Range: -3.0846

Max Act: 3.0214. Min Act: -0.1700

Data Index: 859014 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 3.0846. Min Range: -3.0846

Max Act: 3.0056. Min Act: -0.1700

Data Index: 600858 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 3.0846. Min Range: -3.0846

Max Act: 3.0214. Min Act: -0.1700

Data Index: 34712 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 3.0846. Min Range: -3.0846

Max Act: 3.0214. Min Act: -0.1700

Data Index: 1161058 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9898. Min Act: -0.1700

Data Index: 1220575 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9898. Min Act: -0.1700

Data Index: 868943 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9740. Min Act: -0.1700

Data Index: 637288 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9898. Min Act: -0.1700

Data Index: 841220 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 3.0846. Min Range: -3.0846

Max Act: 3.0056. Min Act: -0.1700

Data Index: 152738 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9898. Min Act: -0.1700

Data Index: 229550 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9740. Min Act: -0.1700

Data Index: 721602 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9740. Min Act: -0.1700

Data Index: 846087 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9581. Min Act: -0.1700

Data Index: 1230932 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 3.0846. Min Range: -3.0846

Max Act: 3.0214. Min Act: -0.1700

Data Index: 968617 (C4 (Web Text))

Max Activating Token Index: 557