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

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

Neuron 1299 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: 3.9157. Min Range: -3.9157

Max Act: 3.9157. Min Act: -0.1700

Data Index: 164601 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 3.9157. Min Range: -3.9157

Max Act: 3.8376. Min Act: -0.1700

Data Index: 702363 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 3.9157. Min Range: -3.9157

Max Act: 3.8063. Min Act: -0.1700

Data Index: 1404184 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.9157. Min Range: -3.9157

Max Act: 3.8219. Min Act: -0.1700

Data Index: 689805 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 3.9157. Min Range: -3.9157

Max Act: 3.7906. Min Act: -0.1700

Data Index: 474272 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 3.9157. Min Range: -3.9157

Max Act: 3.7593. Min Act: -0.1700

Data Index: 1376584 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.9157. Min Range: -3.9157

Max Act: 3.7906. Min Act: -0.1700

Data Index: 1143532 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 3.9157. Min Range: -3.9157

Max Act: 3.8219. Min Act: -0.1700

Data Index: 1337126 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 3.9157. Min Range: -3.9157

Max Act: 3.7906. Min Act: -0.1700

Data Index: 1198409 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 3.9157. Min Range: -3.9157

Max Act: 3.7750. Min Act: -0.1700

Data Index: 263206 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 3.9157. Min Range: -3.9157

Max Act: 3.7906. Min Act: -0.1700

Data Index: 1535102 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 3.9157. Min Range: -3.9157

Max Act: 3.7750. Min Act: -0.1700

Data Index: 1542452 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 3.9157. Min Range: -3.9157

Max Act: 3.7750. Min Act: -0.1700

Data Index: 1359778 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 3.9157. Min Range: -3.9157

Max Act: 3.7593. Min Act: -0.1700

Data Index: 165693 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 3.9157. Min Range: -3.9157

Max Act: 3.7906. Min Act: -0.1700

Data Index: 1029805 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 3.9157. Min Range: -3.9157

Max Act: 3.7593. Min Act: -0.1700

Data Index: 881922 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 3.9157. Min Range: -3.9157

Max Act: 3.7593. Min Act: -0.1700

Data Index: 561148 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 3.9157. Min Range: -3.9157

Max Act: 3.7906. Min Act: -0.1700

Data Index: 551575 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 3.9157. Min Range: -3.9157

Max Act: 3.7593. Min Act: -0.1700

Data Index: 1072592 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 3.9157. Min Range: -3.9157

Max Act: 3.7750. Min Act: -0.1700

Data Index: 1191328 (C4 (Web Text))

Max Activating Token Index: 229