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

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

Neuron 843 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: 2.9451. Min Range: -2.9451

Max Act: 2.9451. Min Act: -0.1700

Data Index: 135019 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.8578. Min Act: -0.1700

Data Index: 759148 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.8232. Min Act: -0.1700

Data Index: 1551050 (Python Code)

Max Activating Token Index: 572

Text #3

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.8219. Min Act: -0.1700

Data Index: 1004215 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.8150. Min Act: -0.1700

Data Index: 1171114 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.8029. Min Act: -0.1700

Data Index: 445862 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7936. Min Act: -0.1700

Data Index: 130253 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7798. Min Act: -0.1700

Data Index: 1641270 (Python Code)

Max Activating Token Index: 194

Text #8

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7882. Min Act: -0.1699

Data Index: 1309114 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7804. Min Act: -0.1700

Data Index: 174925 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7852. Min Act: -0.1700

Data Index: 312040 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.8013. Min Act: -0.1700

Data Index: 162416 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7856. Min Act: -0.1700

Data Index: 1029550 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7539. Min Act: -0.1700

Data Index: 219493 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7693. Min Act: -0.1700

Data Index: 476385 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7670. Min Act: -0.1700

Data Index: 9516 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7744. Min Act: -0.1700

Data Index: 1502563 (Python Code)

Max Activating Token Index: 854

Text #17

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7452. Min Act: -0.1700

Data Index: 1259861 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7600. Min Act: -0.1700

Data Index: 147667 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 2.9451. Min Range: -2.9451

Max Act: 2.7528. Min Act: -0.1700

Data Index: 993310 (C4 (Web Text))

Max Activating Token Index: 815