Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1344 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 6.2854. Min Range: -6.2854

Max Act: 6.2854. Min Act: -0.1700

Data Index: 243381 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 6.2854. Min Range: -6.2854

Max Act: 6.0041. Min Act: -0.1700

Data Index: 704555 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 6.2854. Min Range: -6.2854

Max Act: 6.0354. Min Act: -0.1700

Data Index: 1297543 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 6.2854. Min Range: -6.2854

Max Act: 6.0041. Min Act: -0.1700

Data Index: 928899 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 6.2854. Min Range: -6.2854

Max Act: 6.0041. Min Act: -0.1700

Data Index: 610844 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 6.2854. Min Range: -6.2854

Max Act: 5.9416. Min Act: -0.1700

Data Index: 1282960 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 6.2854. Min Range: -6.2854

Max Act: 5.9416. Min Act: -0.1700

Data Index: 521861 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 6.2854. Min Range: -6.2854

Max Act: 5.9416. Min Act: -0.1700

Data Index: 295428 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 6.2854. Min Range: -6.2854

Max Act: 5.9416. Min Act: -0.1700

Data Index: 534166 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 6.2854. Min Range: -6.2854

Max Act: 5.8166. Min Act: -0.1700

Data Index: 417899 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 6.2854. Min Range: -6.2854

Max Act: 5.9416. Min Act: -0.1700

Data Index: 992136 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 6.2854. Min Range: -6.2854

Max Act: 5.9104. Min Act: -0.1700

Data Index: 1170444 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 6.2854. Min Range: -6.2854

Max Act: 5.8010. Min Act: -0.1700

Data Index: 929751 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 6.2854. Min Range: -6.2854

Max Act: 5.7073. Min Act: -0.1700

Data Index: 712177 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 6.2854. Min Range: -6.2854

Max Act: 5.7385. Min Act: -0.1700

Data Index: 1062265 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 6.2854. Min Range: -6.2854

Max Act: 5.7698. Min Act: -0.1700

Data Index: 962645 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 6.2854. Min Range: -6.2854

Max Act: 5.7385. Min Act: -0.1700

Data Index: 1028964 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 6.2854. Min Range: -6.2854

Max Act: 5.7541. Min Act: -0.1700

Data Index: 49630 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 6.2854. Min Range: -6.2854

Max Act: 5.6760. Min Act: -0.1700

Data Index: 700663 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 6.2854. Min Range: -6.2854

Max Act: 5.6916. Min Act: -0.1700

Data Index: 1580443 (Python Code)

Max Activating Token Index: 838