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

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

Neuron 1317 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.6283. Min Act: -0.1700

Data Index: 1099111 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.6439. Min Act: -0.1700

Data Index: 696999 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.5500. Min Act: -0.1700

Data Index: 314490 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.5500. Min Act: -0.1700

Data Index: 1352496 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.5500. Min Act: -0.1700

Data Index: 310534 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.4873. Min Act: -0.1700

Data Index: 704975 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.5186. Min Act: -0.1700

Data Index: 160725 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.5343. Min Act: -0.1700

Data Index: 1064440 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.5030. Min Act: -0.1700

Data Index: 560498 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.4873. Min Act: -0.1700

Data Index: 725628 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.4716. Min Act: -0.1700

Data Index: 1319354 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.4716. Min Act: -0.1700

Data Index: 1003821 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.4716. Min Act: -0.1700

Data Index: 412196 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.4716. Min Act: -0.1700

Data Index: 1054847 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.4716. Min Act: -0.1700

Data Index: 947581 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.4246. Min Act: -0.1700

Data Index: 758440 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.4560. Min Act: -0.1700

Data Index: 771571 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.4403. Min Act: -0.1700

Data Index: 365719 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.4089. Min Act: -0.1700

Data Index: 340232 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 3.6439. Min Range: -3.6439

Max Act: 3.3932. Min Act: -0.1700

Data Index: 697460 (C4 (Web Text))

Max Activating Token Index: 474