Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 856 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.1439. Min Range: -3.1439

Max Act: 3.1434. Min Act: -0.1699

Data Index: 308909 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 3.1439. Min Range: -3.1439

Max Act: 3.1439. Min Act: -0.1692

Data Index: 209316 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 3.1439. Min Range: -3.1439

Max Act: 3.1072. Min Act: -0.1700

Data Index: 573405 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 3.1439. Min Range: -3.1439

Max Act: 3.0484. Min Act: -0.1217

Data Index: 468679 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 3.1439. Min Range: -3.1439

Max Act: 3.0636. Min Act: -0.1617

Data Index: 644001 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 3.1439. Min Range: -3.1439

Max Act: 3.0500. Min Act: -0.0946

Data Index: 143779 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 3.1439. Min Range: -3.1439

Max Act: 3.0467. Min Act: -0.1691

Data Index: 641953 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 3.1439. Min Range: -3.1439

Max Act: 3.0317. Min Act: -0.1700

Data Index: 221469 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 3.1439. Min Range: -3.1439

Max Act: 3.0269. Min Act: -0.1700

Data Index: 549973 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 3.1439. Min Range: -3.1439

Max Act: 3.0331. Min Act: -0.1699

Data Index: 763099 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 3.1439. Min Range: -3.1439

Max Act: 3.0277. Min Act: -0.1700

Data Index: 787782 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 3.1439. Min Range: -3.1439

Max Act: 3.0131. Min Act: -0.1700

Data Index: 484719 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 3.1439. Min Range: -3.1439

Max Act: 3.0080. Min Act: -0.1698

Data Index: 331785 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 3.1439. Min Range: -3.1439

Max Act: 3.0076. Min Act: -0.1700

Data Index: 631876 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 3.1439. Min Range: -3.1439

Max Act: 3.0084. Min Act: -0.1699

Data Index: 1280954 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.9878. Min Act: -0.1700

Data Index: 421979 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.9699. Min Act: -0.1678

Data Index: 900088 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.9733. Min Act: -0.0762

Data Index: 772702 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.9686. Min Act: -0.1700

Data Index: 485421 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.9549. Min Act: -0.1700

Data Index: 642099 (C4 (Web Text))

Max Activating Token Index: 921