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

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

Neuron 1822 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: 7.0243. Min Range: -7.0243

Max Act: 7.0243. Min Act: -0.1700

Data Index: 1464797 (Python Code)

Max Activating Token Index: 816

Text #1

Max Range: 7.0243. Min Range: -7.0243

Max Act: 6.7118. Min Act: -0.1700

Data Index: 508171 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 7.0243. Min Range: -7.0243

Max Act: 6.6806. Min Act: -0.1700

Data Index: 1087604 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 7.0243. Min Range: -7.0243

Max Act: 6.6493. Min Act: -0.1700

Data Index: 1435111 (Python Code)

Max Activating Token Index: 256

Text #4

Max Range: 7.0243. Min Range: -7.0243

Max Act: 6.6181. Min Act: -0.1700

Data Index: 1491900 (Python Code)

Max Activating Token Index: 869

Text #5

Max Range: 7.0243. Min Range: -7.0243

Max Act: 6.6493. Min Act: -0.1700

Data Index: 358996 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 7.0243. Min Range: -7.0243

Max Act: 6.5556. Min Act: -0.1700

Data Index: 1647014 (Python Code)

Max Activating Token Index: 567

Text #7

Max Range: 7.0243. Min Range: -7.0243

Max Act: 6.5868. Min Act: -0.1700

Data Index: 1422365 (Python Code)

Max Activating Token Index: 474

Text #8

Max Range: 7.0243. Min Range: -7.0243

Max Act: 6.5243. Min Act: -0.1700

Data Index: 729217 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 7.0243. Min Range: -7.0243

Max Act: 6.5243. Min Act: -0.1700

Data Index: 1578986 (Python Code)

Max Activating Token Index: 841

Text #10

Max Range: 7.0243. Min Range: -7.0243

Max Act: 6.4931. Min Act: -0.1700

Data Index: 498918 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 7.0243. Min Range: -7.0243

Max Act: 6.4931. Min Act: -0.1700

Data Index: 1372477 (Python Code)

Max Activating Token Index: 986

Text #12

Max Range: 7.0243. Min Range: -7.0243

Max Act: 6.4618. Min Act: -0.1700

Data Index: 1498482 (Python Code)

Max Activating Token Index: 248

Text #13

Max Range: 7.0243. Min Range: -7.0243

Max Act: 6.4618. Min Act: -0.1700

Data Index: 647020 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 7.0243. Min Range: -7.0243

Max Act: 6.3993. Min Act: -0.1700

Data Index: 1549515 (Python Code)

Max Activating Token Index: 881

Text #15

Max Range: 7.0243. Min Range: -7.0243

Max Act: 6.3993. Min Act: -0.1700

Data Index: 1635271 (Python Code)

Max Activating Token Index: 473

Text #16

Max Range: 7.0243. Min Range: -7.0243

Max Act: 6.3993. Min Act: -0.1700

Data Index: 197924 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 7.0243. Min Range: -7.0243

Max Act: 6.3993. Min Act: -0.1700

Data Index: 574759 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 7.0243. Min Range: -7.0243

Max Act: 6.3993. Min Act: -0.1700

Data Index: 1410420 (Python Code)

Max Activating Token Index: 716

Text #19

Max Range: 7.0243. Min Range: -7.0243

Max Act: 6.3993. Min Act: -0.1700

Data Index: 1607540 (Python Code)

Max Activating Token Index: 162