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

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

Neuron 1063 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: 5.1773. Min Range: -5.1773

Max Act: 5.1773. Min Act: -0.1700

Data Index: 714267 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 5.1773. Min Range: -5.1773

Max Act: 5.0523. Min Act: -0.1700

Data Index: 969163 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 5.1773. Min Range: -5.1773

Max Act: 5.0835. Min Act: -0.1700

Data Index: 637257 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 5.1773. Min Range: -5.1773

Max Act: 5.0835. Min Act: -0.1700

Data Index: 406019 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 5.1773. Min Range: -5.1773

Max Act: 5.0835. Min Act: -0.1700

Data Index: 374861 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 5.1773. Min Range: -5.1773

Max Act: 5.1148. Min Act: -0.1700

Data Index: 116815 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 5.1773. Min Range: -5.1773

Max Act: 5.0523. Min Act: -0.1700

Data Index: 1161641 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 5.1773. Min Range: -5.1773

Max Act: 5.0835. Min Act: -0.1700

Data Index: 844235 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 5.1773. Min Range: -5.1773

Max Act: 4.9898. Min Act: -0.1700

Data Index: 656088 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 5.1773. Min Range: -5.1773

Max Act: 5.0210. Min Act: -0.1700

Data Index: 1007516 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 5.1773. Min Range: -5.1773

Max Act: 5.0210. Min Act: -0.1700

Data Index: 541676 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 5.1773. Min Range: -5.1773

Max Act: 5.0210. Min Act: -0.1700

Data Index: 1068465 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 5.1773. Min Range: -5.1773

Max Act: 4.9898. Min Act: -0.1700

Data Index: 418712 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 5.1773. Min Range: -5.1773

Max Act: 4.9898. Min Act: -0.1700

Data Index: 157029 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 5.1773. Min Range: -5.1773

Max Act: 5.0210. Min Act: -0.1700

Data Index: 800354 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 5.1773. Min Range: -5.1773

Max Act: 4.9898. Min Act: -0.1700

Data Index: 564460 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 5.1773. Min Range: -5.1773

Max Act: 5.0210. Min Act: -0.1700

Data Index: 650845 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 5.1773. Min Range: -5.1773

Max Act: 5.0210. Min Act: -0.1699

Data Index: 270510 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 5.1773. Min Range: -5.1773

Max Act: 4.9585. Min Act: -0.1700

Data Index: 615075 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 5.1773. Min Range: -5.1773

Max Act: 5.0523. Min Act: -0.1700

Data Index: 1142547 (C4 (Web Text))

Max Activating Token Index: 1005