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

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

Neuron 399 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.8222. Min Act: -0.1700

Data Index: 682124 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.8222. Min Act: -0.1700

Data Index: 999692 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.7283. Min Act: -0.1700

Data Index: 1030691 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.7283. Min Act: -0.1700

Data Index: 235605 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.7596. Min Act: -0.1700

Data Index: 670975 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.6814. Min Act: -0.1700

Data Index: 853722 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.7127. Min Act: -0.1700

Data Index: 135839 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.6814. Min Act: -0.1700

Data Index: 253352 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.7283. Min Act: -0.1700

Data Index: 476027 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.6501. Min Act: -0.1700

Data Index: 306269 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.6657. Min Act: -0.1700

Data Index: 488693 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.6657. Min Act: -0.1700

Data Index: 139660 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.6344. Min Act: -0.1700

Data Index: 874904 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.6501. Min Act: -0.1700

Data Index: 404406 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.6814. Min Act: -0.1700

Data Index: 526838 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.6188. Min Act: -0.1700

Data Index: 629249 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.6501. Min Act: -0.1700

Data Index: 375410 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.6657. Min Act: -0.1700

Data Index: 97557 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.6657. Min Act: -0.1700

Data Index: 228521 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 3.8222. Min Range: -3.8222

Max Act: 3.6188. Min Act: -0.1700

Data Index: 21911 (C4 (Web Text))

Max Activating Token Index: 669