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

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

Neuron 902 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: 3.3559. Min Range: -3.3559

Max Act: 3.3559. Min Act: -0.1700

Data Index: 365136 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 3.3559. Min Range: -3.3559

Max Act: 3.2617. Min Act: -0.1700

Data Index: 540075 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 3.3559. Min Range: -3.3559

Max Act: 3.2460. Min Act: -0.1700

Data Index: 913327 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 3.3559. Min Range: -3.3559

Max Act: 3.2302. Min Act: -0.1700

Data Index: 1239646 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 3.3559. Min Range: -3.3559

Max Act: 3.1673. Min Act: -0.1700

Data Index: 318389 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 3.3559. Min Range: -3.3559

Max Act: 3.1673. Min Act: -0.1700

Data Index: 916213 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 3.3559. Min Range: -3.3559

Max Act: 3.1200. Min Act: -0.1700

Data Index: 1029934 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 3.3559. Min Range: -3.3559

Max Act: 3.1358. Min Act: -0.1700

Data Index: 1097842 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 3.3559. Min Range: -3.3559

Max Act: 3.1358. Min Act: -0.1700

Data Index: 1281880 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 3.3559. Min Range: -3.3559

Max Act: 3.1200. Min Act: -0.1700

Data Index: 533794 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 3.3559. Min Range: -3.3559

Max Act: 3.1358. Min Act: -0.1700

Data Index: 658010 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 3.3559. Min Range: -3.3559

Max Act: 3.1358. Min Act: -0.1700

Data Index: 150207 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 3.3559. Min Range: -3.3559

Max Act: 3.1043. Min Act: -0.1700

Data Index: 48943 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 3.3559. Min Range: -3.3559

Max Act: 3.1043. Min Act: -0.1700

Data Index: 819746 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 3.3559. Min Range: -3.3559

Max Act: 3.1043. Min Act: -0.1700

Data Index: 1302526 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 3.3559. Min Range: -3.3559

Max Act: 3.1043. Min Act: -0.1700

Data Index: 859709 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 3.3559. Min Range: -3.3559

Max Act: 3.0885. Min Act: -0.1700

Data Index: 1139693 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 3.3559. Min Range: -3.3559

Max Act: 3.0570. Min Act: -0.1700

Data Index: 588733 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 3.3559. Min Range: -3.3559

Max Act: 3.0727. Min Act: -0.1700

Data Index: 399025 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 3.3559. Min Range: -3.3559

Max Act: 3.0885. Min Act: -0.1700

Data Index: 1293859 (C4 (Web Text))

Max Activating Token Index: 275