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

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

Neuron 790 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: 4.4812. Min Range: -4.4812

Max Act: 4.4812. Min Act: -0.1700

Data Index: 59803 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 4.4812. Min Range: -4.4812

Max Act: 4.3590. Min Act: -0.1700

Data Index: 1359002 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 4.4812. Min Range: -4.4812

Max Act: 4.2834. Min Act: -0.1700

Data Index: 67236 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 4.4812. Min Range: -4.4812

Max Act: 4.2789. Min Act: -0.1700

Data Index: 874262 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 4.4812. Min Range: -4.4812

Max Act: 4.2435. Min Act: -0.1699

Data Index: 1581720 (Python Code)

Max Activating Token Index: 464

Text #5

Max Range: 4.4812. Min Range: -4.4812

Max Act: 4.2723. Min Act: -0.1700

Data Index: 903412 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 4.4812. Min Range: -4.4812

Max Act: 4.2008. Min Act: -0.1700

Data Index: 932676 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 4.4812. Min Range: -4.4812

Max Act: 4.2722. Min Act: -0.1700

Data Index: 854005 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 4.4812. Min Range: -4.4812

Max Act: 4.1822. Min Act: -0.1700

Data Index: 359443 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 4.4812. Min Range: -4.4812

Max Act: 4.1673. Min Act: -0.1700

Data Index: 25287 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 4.4812. Min Range: -4.4812

Max Act: 4.1560. Min Act: -0.1700

Data Index: 953908 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 4.4812. Min Range: -4.4812

Max Act: 4.1549. Min Act: -0.1699

Data Index: 118022 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 4.4812. Min Range: -4.4812

Max Act: 4.1864. Min Act: -0.1700

Data Index: 416572 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 4.4812. Min Range: -4.4812

Max Act: 4.1383. Min Act: -0.1700

Data Index: 961625 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 4.4812. Min Range: -4.4812

Max Act: 4.1050. Min Act: -0.1700

Data Index: 1119916 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 4.4812. Min Range: -4.4812

Max Act: 4.0878. Min Act: -0.1697

Data Index: 161069 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 4.4812. Min Range: -4.4812

Max Act: 4.1241. Min Act: -0.1700

Data Index: 301410 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 4.4812. Min Range: -4.4812

Max Act: 4.0696. Min Act: -0.1700

Data Index: 1342398 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 4.4812. Min Range: -4.4812

Max Act: 4.1027. Min Act: -0.1700

Data Index: 22319 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 4.4812. Min Range: -4.4812

Max Act: 4.1128. Min Act: -0.1700

Data Index: 1610771 (Python Code)

Max Activating Token Index: 782