Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 689 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.3590. Min Act: -0.1700

Data Index: 568822 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.2962. Min Act: -0.1700

Data Index: 1301611 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.2647. Min Act: -0.1700

Data Index: 893322 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.2647. Min Act: -0.1700

Data Index: 414881 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.2804. Min Act: -0.1700

Data Index: 95039 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.2490. Min Act: -0.1700

Data Index: 550832 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.2490. Min Act: -0.1700

Data Index: 38492 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.2176. Min Act: -0.1700

Data Index: 225300 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.1861. Min Act: -0.1700

Data Index: 120412 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.1861. Min Act: -0.1700

Data Index: 962425 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.1861. Min Act: -0.1700

Data Index: 1158706 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.1546. Min Act: -0.1700

Data Index: 296630 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.1704. Min Act: -0.1700

Data Index: 1161732 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.1861. Min Act: -0.1700

Data Index: 315751 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.1389. Min Act: -0.1700

Data Index: 712421 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.1231. Min Act: -0.1700

Data Index: 299513 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.1074. Min Act: -0.1700

Data Index: 1542782 (Python Code)

Max Activating Token Index: 59

Text #17

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.1074. Min Act: -0.1700

Data Index: 29042 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.1231. Min Act: -0.1700

Data Index: 549153 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 3.3590. Min Range: -3.3590

Max Act: 3.1231. Min Act: -0.1700

Data Index: 1127599 (C4 (Web Text))

Max Activating Token Index: 768