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

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

Neuron 1384 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: 3.7234. Min Range: -3.7234

Max Act: 3.7234. Min Act: -0.1700

Data Index: 1129297 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.6921. Min Act: -0.1700

Data Index: 430066 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.6921. Min Act: -0.1700

Data Index: 704657 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.6295. Min Act: -0.1700

Data Index: 847617 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.5982. Min Act: -0.1700

Data Index: 1118934 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.5826. Min Act: -0.1700

Data Index: 326272 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.5199. Min Act: -0.1700

Data Index: 353703 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.4729. Min Act: -0.1700

Data Index: 327799 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.4886. Min Act: -0.1700

Data Index: 251964 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.4572. Min Act: -0.1700

Data Index: 1179327 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.4572. Min Act: -0.1700

Data Index: 359289 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.4416. Min Act: -0.1700

Data Index: 773114 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.4102. Min Act: -0.1700

Data Index: 771713 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.4259. Min Act: -0.1700

Data Index: 386259 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.4416. Min Act: -0.1700

Data Index: 811666 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.4572. Min Act: -0.1700

Data Index: 1147951 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.4259. Min Act: -0.1700

Data Index: 65899 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.4102. Min Act: -0.1700

Data Index: 329643 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.3945. Min Act: -0.1700

Data Index: 1130195 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.3631. Min Act: -0.1700

Data Index: 935408 (C4 (Web Text))

Max Activating Token Index: 1009