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

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

Neuron 1343 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: 11.3343. Min Range: -11.3343

Max Act: 11.3343. Min Act: -0.1700

Data Index: 1630695 (Python Code)

Max Activating Token Index: 484

Text #1

Max Range: 11.3343. Min Range: -11.3343

Max Act: 10.9684. Min Act: -0.1700

Data Index: 564233 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 11.3343. Min Range: -11.3343

Max Act: 10.9278. Min Act: -0.1700

Data Index: 70595 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 11.3343. Min Range: -11.3343

Max Act: 10.9170. Min Act: -0.1700

Data Index: 708571 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 11.3343. Min Range: -11.3343

Max Act: 10.6921. Min Act: -0.1700

Data Index: 1012919 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 11.3343. Min Range: -11.3343

Max Act: 10.7425. Min Act: -0.1700

Data Index: 5479 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 11.3343. Min Range: -11.3343

Max Act: 10.6285. Min Act: -0.1700

Data Index: 1219819 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 11.3343. Min Range: -11.3343

Max Act: 10.6274. Min Act: -0.1700

Data Index: 148792 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 11.3343. Min Range: -11.3343

Max Act: 10.6389. Min Act: -0.1700

Data Index: 77843 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 11.3343. Min Range: -11.3343

Max Act: 10.6556. Min Act: -0.1700

Data Index: 463915 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 11.3343. Min Range: -11.3343

Max Act: 10.6032. Min Act: -0.1700

Data Index: 1437666 (Python Code)

Max Activating Token Index: 391

Text #11

Max Range: 11.3343. Min Range: -11.3343

Max Act: 10.5879. Min Act: -0.1700

Data Index: 476085 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 11.3343. Min Range: -11.3343

Max Act: 10.4765. Min Act: -0.1700

Data Index: 285799 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 11.3343. Min Range: -11.3343

Max Act: 10.5550. Min Act: -0.1700

Data Index: 174821 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 11.3343. Min Range: -11.3343

Max Act: 10.4036. Min Act: -0.1700

Data Index: 672646 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 11.3343. Min Range: -11.3343

Max Act: 10.4862. Min Act: -0.1700

Data Index: 663864 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 11.3343. Min Range: -11.3343

Max Act: 10.4576. Min Act: -0.1700

Data Index: 1579452 (Python Code)

Max Activating Token Index: 130

Text #17

Max Range: 11.3343. Min Range: -11.3343

Max Act: 10.3773. Min Act: -0.1700

Data Index: 874111 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 11.3343. Min Range: -11.3343

Max Act: 10.3754. Min Act: -0.1700

Data Index: 983176 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 11.3343. Min Range: -11.3343

Max Act: 10.3192. Min Act: -0.1700

Data Index: 1030977 (C4 (Web Text))

Max Activating Token Index: 361