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

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

Neuron 644 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: 5.5312. Min Range: -5.5312

Max Act: 5.5312. Min Act: -0.1700

Data Index: 789733 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 5.5312. Min Range: -5.5312

Max Act: 5.4687. Min Act: -0.1700

Data Index: 229483 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 5.5312. Min Range: -5.5312

Max Act: 5.4375. Min Act: -0.1700

Data Index: 349473 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 5.5312. Min Range: -5.5312

Max Act: 5.4062. Min Act: -0.1700

Data Index: 1272207 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 5.5312. Min Range: -5.5312

Max Act: 5.4062. Min Act: -0.1700

Data Index: 279783 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 5.5312. Min Range: -5.5312

Max Act: 5.3750. Min Act: -0.1700

Data Index: 255706 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 5.5312. Min Range: -5.5312

Max Act: 5.4062. Min Act: -0.1700

Data Index: 34091 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 5.5312. Min Range: -5.5312

Max Act: 5.3750. Min Act: -0.1700

Data Index: 396250 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 5.5312. Min Range: -5.5312

Max Act: 5.3437. Min Act: -0.1700

Data Index: 287749 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 5.5312. Min Range: -5.5312

Max Act: 5.3125. Min Act: -0.1700

Data Index: 882867 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 5.5312. Min Range: -5.5312

Max Act: 5.3125. Min Act: -0.1700

Data Index: 980783 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 5.5312. Min Range: -5.5312

Max Act: 5.3437. Min Act: -0.1700

Data Index: 675238 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 5.5312. Min Range: -5.5312

Max Act: 5.2812. Min Act: -0.1700

Data Index: 66983 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 5.5312. Min Range: -5.5312

Max Act: 5.2500. Min Act: -0.1700

Data Index: 337636 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 5.5312. Min Range: -5.5312

Max Act: 5.2812. Min Act: -0.1700

Data Index: 1011204 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 5.5312. Min Range: -5.5312

Max Act: 5.2187. Min Act: -0.1700

Data Index: 897453 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 5.5312. Min Range: -5.5312

Max Act: 5.2187. Min Act: -0.1700

Data Index: 268810 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 5.5312. Min Range: -5.5312

Max Act: 5.2187. Min Act: -0.1700

Data Index: 109907 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 5.5312. Min Range: -5.5312

Max Act: 5.2187. Min Act: -0.1700

Data Index: 992068 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 5.5312. Min Range: -5.5312

Max Act: 5.1875. Min Act: -0.1700

Data Index: 1029255 (C4 (Web Text))

Max Activating Token Index: 484