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

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

Neuron 1208 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: 8.7810. Min Range: -8.7810

Max Act: 8.7810. Min Act: -0.1700

Data Index: 744894 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 8.7810. Min Range: -8.7810

Max Act: 8.7008. Min Act: -0.1700

Data Index: 1428476 (Python Code)

Max Activating Token Index: 537

Text #2

Max Range: 8.7810. Min Range: -8.7810

Max Act: 8.6898. Min Act: -0.1700

Data Index: 1391917 (Python Code)

Max Activating Token Index: 661

Text #3

Max Range: 8.7810. Min Range: -8.7810

Max Act: 8.4250. Min Act: -0.1700

Data Index: 1190268 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 8.7810. Min Range: -8.7810

Max Act: 8.3140. Min Act: -0.1700

Data Index: 705392 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 8.7810. Min Range: -8.7810

Max Act: 8.2964. Min Act: -0.1700

Data Index: 850523 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 8.7810. Min Range: -8.7810

Max Act: 8.1752. Min Act: -0.1700

Data Index: 496399 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 8.7810. Min Range: -8.7810

Max Act: 8.1731. Min Act: -0.1700

Data Index: 292383 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 8.7810. Min Range: -8.7810

Max Act: 8.1164. Min Act: -0.1700

Data Index: 415488 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 8.7810. Min Range: -8.7810

Max Act: 8.0625. Min Act: -0.1700

Data Index: 1316251 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 8.7810. Min Range: -8.7810

Max Act: 8.0337. Min Act: -0.1700

Data Index: 796401 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 8.7810. Min Range: -8.7810

Max Act: 8.0284. Min Act: -0.1700

Data Index: 367965 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 8.7810. Min Range: -8.7810

Max Act: 7.9737. Min Act: -0.1700

Data Index: 561123 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 8.7810. Min Range: -8.7810

Max Act: 7.9801. Min Act: -0.1700

Data Index: 190810 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 8.7810. Min Range: -8.7810

Max Act: 8.0373. Min Act: -0.1700

Data Index: 1415716 (Python Code)

Max Activating Token Index: 867

Text #15

Max Range: 8.7810. Min Range: -8.7810

Max Act: 7.9029. Min Act: -0.1700

Data Index: 182574 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 8.7810. Min Range: -8.7810

Max Act: 7.9414. Min Act: -0.1700

Data Index: 627331 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 8.7810. Min Range: -8.7810

Max Act: 7.9150. Min Act: -0.1700

Data Index: 169830 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 8.7810. Min Range: -8.7810

Max Act: 7.8714. Min Act: -0.1700

Data Index: 635095 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 8.7810. Min Range: -8.7810

Max Act: 7.9222. Min Act: -0.1700

Data Index: 343822 (C4 (Web Text))

Max Activating Token Index: 6