Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1677 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.1274. Min Range: -5.1274

Max Act: 5.1274. Min Act: -0.1700

Data Index: 537242 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 5.1274. Min Range: -5.1274

Max Act: 5.0649. Min Act: -0.1700

Data Index: 909704 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 5.1274. Min Range: -5.1274

Max Act: 5.0337. Min Act: -0.1700

Data Index: 33074 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 5.1274. Min Range: -5.1274

Max Act: 5.0024. Min Act: -0.1700

Data Index: 245098 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9712. Min Act: -0.1700

Data Index: 1317350 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 5.1274. Min Range: -5.1274

Max Act: 5.0024. Min Act: -0.1700

Data Index: 123131 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9712. Min Act: -0.1700

Data Index: 777582 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9087. Min Act: -0.1700

Data Index: 1096301 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.8774. Min Act: -0.1700

Data Index: 496795 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.8774. Min Act: -0.1700

Data Index: 114645 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9399. Min Act: -0.1700

Data Index: 1059813 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9087. Min Act: -0.1700

Data Index: 218957 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9087. Min Act: -0.1700

Data Index: 290552 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.7837. Min Act: -0.1700

Data Index: 352702 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.8149. Min Act: -0.1700

Data Index: 171644 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.8462. Min Act: -0.1700

Data Index: 619954 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.8149. Min Act: -0.1700

Data Index: 464674 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.8149. Min Act: -0.1700

Data Index: 232548 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.7837. Min Act: -0.1700

Data Index: 617806 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.8149. Min Act: -0.1700

Data Index: 536458 (C4 (Web Text))

Max Activating Token Index: 899