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

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

Neuron 869 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: 5.1113. Min Range: -5.1113

Max Act: 5.1113. Min Act: -0.1700

Data Index: 816319 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 5.1113. Min Range: -5.1113

Max Act: 5.0487. Min Act: -0.1700

Data Index: 329339 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 5.1113. Min Range: -5.1113

Max Act: 5.1113. Min Act: -0.1700

Data Index: 956816 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 5.1113. Min Range: -5.1113

Max Act: 4.9862. Min Act: -0.1700

Data Index: 1093146 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 5.1113. Min Range: -5.1113

Max Act: 5.0175. Min Act: -0.1700

Data Index: 1299718 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 5.1113. Min Range: -5.1113

Max Act: 5.0175. Min Act: -0.1700

Data Index: 1004856 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 5.1113. Min Range: -5.1113

Max Act: 4.9862. Min Act: -0.1700

Data Index: 617785 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 5.1113. Min Range: -5.1113

Max Act: 5.0175. Min Act: -0.1700

Data Index: 935171 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 5.1113. Min Range: -5.1113

Max Act: 5.0175. Min Act: -0.1700

Data Index: 995776 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 5.1113. Min Range: -5.1113

Max Act: 4.9862. Min Act: -0.1700

Data Index: 374847 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 5.1113. Min Range: -5.1113

Max Act: 4.9862. Min Act: -0.1700

Data Index: 771695 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 5.1113. Min Range: -5.1113

Max Act: 5.0800. Min Act: -0.1700

Data Index: 456422 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 5.1113. Min Range: -5.1113

Max Act: 4.9550. Min Act: -0.1699

Data Index: 38025 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 5.1113. Min Range: -5.1113

Max Act: 5.0487. Min Act: -0.1700

Data Index: 458548 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 5.1113. Min Range: -5.1113

Max Act: 4.9862. Min Act: -0.1700

Data Index: 769783 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 5.1113. Min Range: -5.1113

Max Act: 4.9550. Min Act: -0.1700

Data Index: 256498 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 5.1113. Min Range: -5.1113

Max Act: 4.9550. Min Act: -0.1700

Data Index: 1069200 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 5.1113. Min Range: -5.1113

Max Act: 4.9550. Min Act: -0.1700

Data Index: 787031 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 5.1113. Min Range: -5.1113

Max Act: 4.9862. Min Act: -0.1700

Data Index: 29560 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 5.1113. Min Range: -5.1113

Max Act: 4.9237. Min Act: -0.1700

Data Index: 627654 (C4 (Web Text))

Max Activating Token Index: 385