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

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

Neuron 929 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.4390. Min Act: -0.1700

Data Index: 908870 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.3449. Min Act: -0.1700

Data Index: 1319568 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.3763. Min Act: -0.1700

Data Index: 1316063 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.3449. Min Act: -0.1700

Data Index: 339139 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.2821. Min Act: -0.1700

Data Index: 940732 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.2507. Min Act: -0.1700

Data Index: 965693 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.2507. Min Act: -0.1700

Data Index: 680668 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.2192. Min Act: -0.1700

Data Index: 390999 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.1878. Min Act: -0.1700

Data Index: 174336 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.2192. Min Act: -0.1700

Data Index: 1045788 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.2192. Min Act: -0.1700

Data Index: 1299041 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.1563. Min Act: -0.1700

Data Index: 930102 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.1878. Min Act: -0.1700

Data Index: 880202 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.1563. Min Act: -0.1700

Data Index: 964313 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.1878. Min Act: -0.1700

Data Index: 1150320 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.1878. Min Act: -0.1700

Data Index: 422987 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.1563. Min Act: -0.1700

Data Index: 1127155 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.1878. Min Act: -0.1700

Data Index: 785294 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.1248. Min Act: -0.1700

Data Index: 569913 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 3.4390. Min Range: -3.4390

Max Act: 3.1563. Min Act: -0.1700

Data Index: 1108164 (C4 (Web Text))

Max Activating Token Index: 384