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

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

Neuron 93 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1274. Min Range: -5.1274

Max Act: 5.1274. Min Act: -0.1699

Data Index: 352553 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 5.1274. Min Range: -5.1274

Max Act: 5.1274. Min Act: -0.1700

Data Index: 797316 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 5.1274. Min Range: -5.1274

Max Act: 5.0961. Min Act: -0.1700

Data Index: 596500 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 5.1274. Min Range: -5.1274

Max Act: 5.0961. Min Act: -0.1700

Data Index: 1168816 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 5.1274. Min Range: -5.1274

Max Act: 5.0024. Min Act: -0.1700

Data Index: 912123 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 5.1274. Min Range: -5.1274

Max Act: 5.0649. Min Act: -0.1700

Data Index: 1299595 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 5.1274. Min Range: -5.1274

Max Act: 5.0649. Min Act: -0.1700

Data Index: 438991 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 5.1274. Min Range: -5.1274

Max Act: 5.0336. Min Act: -0.1700

Data Index: 426360 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9711. Min Act: -0.1700

Data Index: 1057366 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 5.1274. Min Range: -5.1274

Max Act: 5.0336. Min Act: -0.1700

Data Index: 110893 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9711. Min Act: -0.1700

Data Index: 445316 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9399. Min Act: -0.1700

Data Index: 557965 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9399. Min Act: -0.1699

Data Index: 572453 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9399. Min Act: -0.1700

Data Index: 1111155 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9086. Min Act: -0.1700

Data Index: 359949 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9399. Min Act: -0.1700

Data Index: 130192 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9399. Min Act: -0.1700

Data Index: 105301 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9711. Min Act: -0.1700

Data Index: 1300411 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.8774. Min Act: -0.1700

Data Index: 602684 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.8149. Min Act: -0.1700

Data Index: 823837 (C4 (Web Text))

Max Activating Token Index: 366