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

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

Neuron 667 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.1720. Min Range: -5.1720

Max Act: 5.1720. Min Act: -0.1700

Data Index: 802582 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.8282. Min Act: -0.1700

Data Index: 452595 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.7657. Min Act: -0.1700

Data Index: 1255555 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.7345. Min Act: -0.1700

Data Index: 155212 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.7657. Min Act: -0.1700

Data Index: 230886 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.7032. Min Act: -0.1700

Data Index: 412840 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.7345. Min Act: -0.1700

Data Index: 1062175 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.7032. Min Act: -0.1700

Data Index: 85714 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.6407. Min Act: -0.1700

Data Index: 871795 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.6095. Min Act: -0.1700

Data Index: 114655 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.6407. Min Act: -0.1700

Data Index: 560456 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.6720. Min Act: -0.1700

Data Index: 687723 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.6407. Min Act: -0.1700

Data Index: 541306 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.6407. Min Act: -0.1700

Data Index: 1018318 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.5782. Min Act: -0.1700

Data Index: 1166434 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.5157. Min Act: -0.1699

Data Index: 1062629 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.5782. Min Act: -0.1700

Data Index: 717 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.5782. Min Act: -0.1700

Data Index: 291597 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.5470. Min Act: -0.1700

Data Index: 80151 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.5157. Min Act: -0.1699

Data Index: 1062831 (C4 (Web Text))

Max Activating Token Index: 711