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

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

Neuron 1592 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: 3.4628. Min Range: -3.4628

Max Act: 3.4628. Min Act: -0.1700

Data Index: 871124 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.3740. Min Act: -0.1700

Data Index: 230118 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.3241. Min Act: -0.1700

Data Index: 892953 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.2614. Min Act: -0.1700

Data Index: 1231585 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.2488. Min Act: -0.1699

Data Index: 23657 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.1972. Min Act: -0.1700

Data Index: 609734 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.2043. Min Act: -0.1700

Data Index: 293582 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.2115. Min Act: -0.1700

Data Index: 227679 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.1690. Min Act: -0.1700

Data Index: 122318 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.1586. Min Act: -0.1700

Data Index: 1050899 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.1368. Min Act: -0.1699

Data Index: 935463 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.1449. Min Act: -0.1700

Data Index: 823857 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.1283. Min Act: -0.1700

Data Index: 977046 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.0913. Min Act: -0.1700

Data Index: 539989 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.0935. Min Act: -0.1700

Data Index: 841279 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.1009. Min Act: -0.1700

Data Index: 229915 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.0825. Min Act: -0.1700

Data Index: 347768 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.0580. Min Act: -0.1700

Data Index: 230180 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.0652. Min Act: -0.1700

Data Index: 322435 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.0477. Min Act: -0.1700

Data Index: 701425 (C4 (Web Text))

Max Activating Token Index: 1014