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

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

Neuron 1882 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.8766. Min Act: -0.1700

Data Index: 1071597 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.5953. Min Act: -0.1700

Data Index: 1241752 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.5328. Min Act: -0.1700

Data Index: 567271 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.5328. Min Act: -0.1700

Data Index: 1332536 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.5640. Min Act: -0.1700

Data Index: 794523 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.5640. Min Act: -0.1700

Data Index: 614266 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.5328. Min Act: -0.1700

Data Index: 1062158 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.5015. Min Act: -0.1700

Data Index: 149097 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.4390. Min Act: -0.1700

Data Index: 294272 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.4703. Min Act: -0.1700

Data Index: 124245 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.4078. Min Act: -0.1700

Data Index: 1349270 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.4078. Min Act: -0.1700

Data Index: 434114 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.4078. Min Act: -0.1700

Data Index: 630614 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.4078. Min Act: -0.1700

Data Index: 563020 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.4078. Min Act: -0.1700

Data Index: 12381 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.4078. Min Act: -0.1700

Data Index: 578015 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.3453. Min Act: -0.1700

Data Index: 855700 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.3765. Min Act: -0.1700

Data Index: 234959 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.4078. Min Act: -0.1700

Data Index: 490996 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.3765. Min Act: -0.1700

Data Index: 474150 (C4 (Web Text))

Max Activating Token Index: 270