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

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

Neuron 1842 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: 3.3282. Min Range: -3.3282

Max Act: 3.3282. Min Act: -0.1700

Data Index: 1126006 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 3.3282. Min Range: -3.3282

Max Act: 3.3125. Min Act: -0.1700

Data Index: 1569569 (Python Code)

Max Activating Token Index: 978

Text #2

Max Range: 3.3282. Min Range: -3.3282

Max Act: 3.3125. Min Act: -0.1700

Data Index: 586797 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 3.3282. Min Range: -3.3282

Max Act: 3.2968. Min Act: -0.1700

Data Index: 1478 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 3.3282. Min Range: -3.3282

Max Act: 3.2968. Min Act: -0.1700

Data Index: 1510229 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 3.3282. Min Range: -3.3282

Max Act: 3.2968. Min Act: -0.1700

Data Index: 566957 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 3.3282. Min Range: -3.3282

Max Act: 3.2654. Min Act: -0.1700

Data Index: 624689 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 3.3282. Min Range: -3.3282

Max Act: 3.2654. Min Act: -0.1700

Data Index: 517129 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 3.3282. Min Range: -3.3282

Max Act: 3.2654. Min Act: -0.1700

Data Index: 847679 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 3.3282. Min Range: -3.3282

Max Act: 3.2339. Min Act: -0.1700

Data Index: 319677 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 3.3282. Min Range: -3.3282

Max Act: 3.2339. Min Act: -0.1700

Data Index: 1107524 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 3.3282. Min Range: -3.3282

Max Act: 3.2339. Min Act: -0.1700

Data Index: 1019936 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 3.3282. Min Range: -3.3282

Max Act: 3.2339. Min Act: -0.1700

Data Index: 421367 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 3.3282. Min Range: -3.3282

Max Act: 3.2339. Min Act: -0.1700

Data Index: 1191854 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 3.3282. Min Range: -3.3282

Max Act: 3.2339. Min Act: -0.1700

Data Index: 14607 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 3.3282. Min Range: -3.3282

Max Act: 3.2339. Min Act: -0.1700

Data Index: 480826 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 3.3282. Min Range: -3.3282

Max Act: 3.2339. Min Act: -0.1700

Data Index: 698318 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 3.3282. Min Range: -3.3282

Max Act: 3.2182. Min Act: -0.1700

Data Index: 382249 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 3.3282. Min Range: -3.3282

Max Act: 3.2182. Min Act: -0.1700

Data Index: 752343 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 3.3282. Min Range: -3.3282

Max Act: 3.2025. Min Act: -0.1700

Data Index: 245263 (C4 (Web Text))

Max Activating Token Index: 339