Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1773 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1593. Min Range: -3.1593

Max Act: 3.1593. Min Act: -0.1700

Data Index: 1255717 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 3.1593. Min Range: -3.1593

Max Act: 3.1278. Min Act: -0.1700

Data Index: 873313 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 3.1593. Min Range: -3.1593

Max Act: 3.1278. Min Act: -0.1700

Data Index: 935057 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 3.1593. Min Range: -3.1593

Max Act: 3.0173. Min Act: -0.1700

Data Index: 414723 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 3.1593. Min Range: -3.1593

Max Act: 3.0015. Min Act: -0.1700

Data Index: 140767 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 3.1593. Min Range: -3.1593

Max Act: 2.9857. Min Act: -0.1700

Data Index: 914400 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 3.1593. Min Range: -3.1593

Max Act: 2.9699. Min Act: -0.1700

Data Index: 164579 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 3.1593. Min Range: -3.1593

Max Act: 2.9699. Min Act: -0.1700

Data Index: 1281880 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 3.1593. Min Range: -3.1593

Max Act: 2.9541. Min Act: -0.1700

Data Index: 363815 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 3.1593. Min Range: -3.1593

Max Act: 2.9541. Min Act: -0.1700

Data Index: 915814 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 3.1593. Min Range: -3.1593

Max Act: 2.9382. Min Act: -0.1700

Data Index: 32477 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 3.1593. Min Range: -3.1593

Max Act: 2.9382. Min Act: -0.1700

Data Index: 1142256 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 3.1593. Min Range: -3.1593

Max Act: 2.9382. Min Act: -0.1700

Data Index: 1205196 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 3.1593. Min Range: -3.1593

Max Act: 2.9382. Min Act: -0.1700

Data Index: 301802 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 3.1593. Min Range: -3.1593

Max Act: 2.9224. Min Act: -0.1700

Data Index: 1031607 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 3.1593. Min Range: -3.1593

Max Act: 2.9382. Min Act: -0.1700

Data Index: 766774 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 3.1593. Min Range: -3.1593

Max Act: 2.9224. Min Act: -0.1700

Data Index: 387925 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 3.1593. Min Range: -3.1593

Max Act: 2.9224. Min Act: -0.1700

Data Index: 943241 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 3.1593. Min Range: -3.1593

Max Act: 2.9224. Min Act: -0.1700

Data Index: 314741 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 3.1593. Min Range: -3.1593

Max Act: 2.9224. Min Act: -0.1700

Data Index: 1044559 (C4 (Web Text))

Max Activating Token Index: 34