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

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

Neuron 1497 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: 5.2463. Min Range: -5.2463

Max Act: 5.2151. Min Act: -0.1700

Data Index: 1272763 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 5.2463. Min Range: -5.2463

Max Act: 5.2463. Min Act: -0.1700

Data Index: 506393 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 5.2463. Min Range: -5.2463

Max Act: 5.2151. Min Act: -0.1700

Data Index: 699234 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 5.2463. Min Range: -5.2463

Max Act: 5.1526. Min Act: -0.1700

Data Index: 314234 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 5.2463. Min Range: -5.2463

Max Act: 5.1213. Min Act: -0.1700

Data Index: 1197166 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 5.2463. Min Range: -5.2463

Max Act: 5.1213. Min Act: -0.1700

Data Index: 354412 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 5.2463. Min Range: -5.2463

Max Act: 5.1213. Min Act: -0.1700

Data Index: 140623 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 5.2463. Min Range: -5.2463

Max Act: 5.0588. Min Act: -0.1700

Data Index: 752800 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 5.2463. Min Range: -5.2463

Max Act: 5.0276. Min Act: -0.1700

Data Index: 931953 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 5.2463. Min Range: -5.2463

Max Act: 4.9651. Min Act: -0.1700

Data Index: 716094 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 5.2463. Min Range: -5.2463

Max Act: 4.9651. Min Act: -0.1700

Data Index: 236791 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 5.2463. Min Range: -5.2463

Max Act: 4.9026. Min Act: -0.1700

Data Index: 721739 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 5.2463. Min Range: -5.2463

Max Act: 4.9338. Min Act: -0.1700

Data Index: 1313682 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 5.2463. Min Range: -5.2463

Max Act: 4.8713. Min Act: -0.1700

Data Index: 356197 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 5.2463. Min Range: -5.2463

Max Act: 4.8401. Min Act: -0.1700

Data Index: 508137 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 5.2463. Min Range: -5.2463

Max Act: 4.8088. Min Act: -0.1700

Data Index: 1083005 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 5.2463. Min Range: -5.2463

Max Act: 4.8088. Min Act: -0.1700

Data Index: 356985 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 5.2463. Min Range: -5.2463

Max Act: 4.8401. Min Act: -0.1700

Data Index: 630782 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 5.2463. Min Range: -5.2463

Max Act: 4.7776. Min Act: -0.1700

Data Index: 515110 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 5.2463. Min Range: -5.2463

Max Act: 4.8401. Min Act: -0.1699

Data Index: 1059745 (C4 (Web Text))

Max Activating Token Index: 131