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

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

Neuron 1252 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: 3.7969. Min Range: -3.7969

Max Act: 3.7969. Min Act: -0.1696

Data Index: 1406197 (Python Code)

Max Activating Token Index: 62

Text #1

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6578. Min Act: -0.1700

Data Index: 1176890 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6429. Min Act: -0.1697

Data Index: 1593789 (Python Code)

Max Activating Token Index: 952

Text #3

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6671. Min Act: -0.1700

Data Index: 1535165 (Python Code)

Max Activating Token Index: 171

Text #4

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6425. Min Act: -0.1700

Data Index: 1579690 (Python Code)

Max Activating Token Index: 545

Text #5

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6101. Min Act: -0.1695

Data Index: 1466453 (Python Code)

Max Activating Token Index: 674

Text #6

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.5915. Min Act: -0.1700

Data Index: 1370842 (Python Code)

Max Activating Token Index: 739

Text #7

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6123. Min Act: -0.1700

Data Index: 1553070 (Python Code)

Max Activating Token Index: 668

Text #8

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.6068. Min Act: -0.1699

Data Index: 1556334 (Python Code)

Max Activating Token Index: 631

Text #9

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.5533. Min Act: -0.1700

Data Index: 1480333 (Python Code)

Max Activating Token Index: 497

Text #10

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.5361. Min Act: -0.1699

Data Index: 133360 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.5280. Min Act: -0.1700

Data Index: 1547067 (Python Code)

Max Activating Token Index: 538

Text #12

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.5425. Min Act: -0.1700

Data Index: 1614392 (Python Code)

Max Activating Token Index: 902

Text #13

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.5361. Min Act: -0.1698

Data Index: 1004527 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.4985. Min Act: -0.1474

Data Index: 1509099 (Python Code)

Max Activating Token Index: 289

Text #15

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.5214. Min Act: -0.1700

Data Index: 129736 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.5082. Min Act: -0.1700

Data Index: 925590 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.4832. Min Act: -0.1698

Data Index: 1441493 (Python Code)

Max Activating Token Index: 93

Text #18

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.4709. Min Act: -0.1700

Data Index: 1505255 (Python Code)

Max Activating Token Index: 913

Text #19

Max Range: 3.7969. Min Range: -3.7969

Max Act: 3.4631. Min Act: -0.1698

Data Index: 1530744 (Python Code)

Max Activating Token Index: 632