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

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

Neuron 1738 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.8948. Min Act: -0.1700

Data Index: 1050579 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.7697. Min Act: -0.1700

Data Index: 694801 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.8948. Min Act: -0.1700

Data Index: 1106643 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.8323. Min Act: -0.1700

Data Index: 3463 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.9261. Min Act: -0.1700

Data Index: 674197 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.8010. Min Act: -0.1700

Data Index: 257528 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.8323. Min Act: -0.1700

Data Index: 635834 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.8010. Min Act: -0.1700

Data Index: 1089521 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.8010. Min Act: -0.1700

Data Index: 908950 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.8636. Min Act: -0.1700

Data Index: 471308 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.8010. Min Act: -0.1700

Data Index: 532328 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.8010. Min Act: -0.1700

Data Index: 1411210 (Python Code)

Max Activating Token Index: 642

Text #12

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.8010. Min Act: -0.1700

Data Index: 1374665 (Python Code)

Max Activating Token Index: 766

Text #13

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.7697. Min Act: -0.1700

Data Index: 1421342 (Python Code)

Max Activating Token Index: 487

Text #14

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.7697. Min Act: -0.1700

Data Index: 1539002 (Python Code)

Max Activating Token Index: 620

Text #15

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.7697. Min Act: -0.1700

Data Index: 821360 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.8636. Min Act: -0.1700

Data Index: 443452 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.7697. Min Act: -0.1700

Data Index: 333352 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.7384. Min Act: -0.1700

Data Index: 683310 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.8010. Min Act: -0.1700

Data Index: 177029 (C4 (Web Text))

Max Activating Token Index: 423