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

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

Neuron 1050 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: 3.8023. Min Range: -3.8023

Max Act: 3.8023. Min Act: -0.1700

Data Index: 577907 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 3.8023. Min Range: -3.8023

Max Act: 3.7084. Min Act: -0.1700

Data Index: 768470 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 3.8023. Min Range: -3.8023

Max Act: 3.7084. Min Act: -0.1700

Data Index: 265325 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 3.8023. Min Range: -3.8023

Max Act: 3.6145. Min Act: -0.1700

Data Index: 1283952 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 3.8023. Min Range: -3.8023

Max Act: 3.5989. Min Act: -0.1700

Data Index: 1309894 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 3.8023. Min Range: -3.8023

Max Act: 3.5049. Min Act: -0.1700

Data Index: 1317495 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 3.8023. Min Range: -3.8023

Max Act: 3.4892. Min Act: -0.1700

Data Index: 662381 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 3.8023. Min Range: -3.8023

Max Act: 3.4735. Min Act: -0.1700

Data Index: 152904 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 3.8023. Min Range: -3.8023

Max Act: 3.5206. Min Act: -0.1700

Data Index: 224754 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 3.8023. Min Range: -3.8023

Max Act: 3.4892. Min Act: -0.1700

Data Index: 1479863 (Python Code)

Max Activating Token Index: 590

Text #10

Max Range: 3.8023. Min Range: -3.8023

Max Act: 3.4579. Min Act: -0.1700

Data Index: 755968 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 3.8023. Min Range: -3.8023

Max Act: 3.4735. Min Act: -0.1700

Data Index: 1229491 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 3.8023. Min Range: -3.8023

Max Act: 3.4579. Min Act: -0.1700

Data Index: 618725 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 3.8023. Min Range: -3.8023

Max Act: 3.4422. Min Act: -0.1700

Data Index: 1229238 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 3.8023. Min Range: -3.8023

Max Act: 3.4735. Min Act: -0.1700

Data Index: 1482742 (Python Code)

Max Activating Token Index: 519

Text #15

Max Range: 3.8023. Min Range: -3.8023

Max Act: 3.4892. Min Act: -0.1700

Data Index: 969845 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 3.8023. Min Range: -3.8023

Max Act: 3.4579. Min Act: -0.1700

Data Index: 185530 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 3.8023. Min Range: -3.8023

Max Act: 3.4422. Min Act: -0.1700

Data Index: 1224912 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 3.8023. Min Range: -3.8023

Max Act: 3.4265. Min Act: -0.1700

Data Index: 193111 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 3.8023. Min Range: -3.8023

Max Act: 3.4108. Min Act: -0.1700

Data Index: 365289 (C4 (Web Text))

Max Activating Token Index: 687