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

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

Neuron 310 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: 5.3564. Min Range: -5.3564

Max Act: 5.2939. Min Act: -0.1700

Data Index: 101109 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 5.3564. Min Range: -5.3564

Max Act: 5.3564. Min Act: -0.1700

Data Index: 914691 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 5.3564. Min Range: -5.3564

Max Act: 5.2314. Min Act: -0.1700

Data Index: 751919 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 5.3564. Min Range: -5.3564

Max Act: 5.2001. Min Act: -0.1700

Data Index: 767107 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 5.3564. Min Range: -5.3564

Max Act: 5.0751. Min Act: -0.1700

Data Index: 613087 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 5.3564. Min Range: -5.3564

Max Act: 5.1064. Min Act: -0.1700

Data Index: 449171 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 5.3564. Min Range: -5.3564

Max Act: 5.1064. Min Act: -0.1700

Data Index: 1320967 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 5.3564. Min Range: -5.3564

Max Act: 5.0751. Min Act: -0.1700

Data Index: 1228016 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 5.3564. Min Range: -5.3564

Max Act: 5.1376. Min Act: -0.1700

Data Index: 519052 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 5.3564. Min Range: -5.3564

Max Act: 5.1064. Min Act: -0.1700

Data Index: 310816 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 5.3564. Min Range: -5.3564

Max Act: 5.2001. Min Act: -0.1700

Data Index: 687509 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 5.3564. Min Range: -5.3564

Max Act: 5.1064. Min Act: -0.1700

Data Index: 544285 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 5.3564. Min Range: -5.3564

Max Act: 5.1064. Min Act: -0.1700

Data Index: 1357536 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 5.3564. Min Range: -5.3564

Max Act: 5.0126. Min Act: -0.1700

Data Index: 968613 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 5.3564. Min Range: -5.3564

Max Act: 4.9501. Min Act: -0.1700

Data Index: 825054 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 5.3564. Min Range: -5.3564

Max Act: 5.0439. Min Act: -0.1700

Data Index: 1055388 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 5.3564. Min Range: -5.3564

Max Act: 4.9814. Min Act: -0.1700

Data Index: 196994 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 5.3564. Min Range: -5.3564

Max Act: 5.0126. Min Act: -0.1700

Data Index: 847521 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 5.3564. Min Range: -5.3564

Max Act: 5.0126. Min Act: -0.1700

Data Index: 1194113 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 5.3564. Min Range: -5.3564

Max Act: 5.0126. Min Act: -0.1700

Data Index: 445988 (C4 (Web Text))

Max Activating Token Index: 187