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

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

Neuron 1546 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: 3.7300. Min Range: -3.7300

Max Act: 3.7300. Min Act: -0.1700

Data Index: 1629208 (Python Code)

Max Activating Token Index: 476

Text #1

Max Range: 3.7300. Min Range: -3.7300

Max Act: 3.6689. Min Act: -0.1700

Data Index: 1640591 (Python Code)

Max Activating Token Index: 254

Text #2

Max Range: 3.7300. Min Range: -3.7300

Max Act: 3.5841. Min Act: -0.1700

Data Index: 1522014 (Python Code)

Max Activating Token Index: 518

Text #3

Max Range: 3.7300. Min Range: -3.7300

Max Act: 3.5795. Min Act: -0.1700

Data Index: 566044 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 3.7300. Min Range: -3.7300

Max Act: 3.5608. Min Act: -0.1700

Data Index: 954675 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 3.7300. Min Range: -3.7300

Max Act: 3.5486. Min Act: -0.1700

Data Index: 1579086 (Python Code)

Max Activating Token Index: 544

Text #6

Max Range: 3.7300. Min Range: -3.7300

Max Act: 3.5319. Min Act: -0.1700

Data Index: 583603 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 3.7300. Min Range: -3.7300

Max Act: 3.5068. Min Act: -0.1700

Data Index: 1405379 (Python Code)

Max Activating Token Index: 873

Text #8

Max Range: 3.7300. Min Range: -3.7300

Max Act: 3.4832. Min Act: -0.1700

Data Index: 1183388 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 3.7300. Min Range: -3.7300

Max Act: 3.4537. Min Act: -0.1700

Data Index: 792781 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 3.7300. Min Range: -3.7300

Max Act: 3.4604. Min Act: -0.1700

Data Index: 1614881 (Python Code)

Max Activating Token Index: 778

Text #11

Max Range: 3.7300. Min Range: -3.7300

Max Act: 3.4400. Min Act: -0.1700

Data Index: 252007 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 3.7300. Min Range: -3.7300

Max Act: 3.4227. Min Act: -0.1700

Data Index: 804898 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 3.7300. Min Range: -3.7300

Max Act: 3.4156. Min Act: -0.1700

Data Index: 1061100 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 3.7300. Min Range: -3.7300

Max Act: 3.3878. Min Act: -0.1700

Data Index: 121034 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 3.7300. Min Range: -3.7300

Max Act: 3.3902. Min Act: -0.1700

Data Index: 840853 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 3.7300. Min Range: -3.7300

Max Act: 3.3990. Min Act: -0.1700

Data Index: 183165 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 3.7300. Min Range: -3.7300

Max Act: 3.3981. Min Act: -0.1700

Data Index: 1215575 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 3.7300. Min Range: -3.7300

Max Act: 3.3997. Min Act: -0.1700

Data Index: 1110273 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 3.7300. Min Range: -3.7300

Max Act: 3.3798. Min Act: -0.1700

Data Index: 278073 (C4 (Web Text))

Max Activating Token Index: 459