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

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

Neuron 1490 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: 3.1701. Min Range: -3.1701

Max Act: 3.1701. Min Act: -0.1700

Data Index: 1182848 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.1386. Min Act: -0.1700

Data Index: 677849 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.1544. Min Act: -0.1700

Data Index: 232960 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.1544. Min Act: -0.1700

Data Index: 596831 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.1386. Min Act: -0.1700

Data Index: 1315690 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.1071. Min Act: -0.1700

Data Index: 173874 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0913. Min Act: -0.1700

Data Index: 361147 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0756. Min Act: -0.1700

Data Index: 1234064 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0756. Min Act: -0.1700

Data Index: 1015333 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0756. Min Act: -0.1700

Data Index: 973828 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0756. Min Act: -0.1700

Data Index: 973395 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0598. Min Act: -0.1700

Data Index: 1249444 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0440. Min Act: -0.1700

Data Index: 683102 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0282. Min Act: -0.1700

Data Index: 1266092 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0440. Min Act: -0.1700

Data Index: 1108643 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0440. Min Act: -0.1700

Data Index: 410160 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0124. Min Act: -0.1700

Data Index: 1244346 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0282. Min Act: -0.1700

Data Index: 365676 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 3.1701. Min Range: -3.1701

Max Act: 3.0124. Min Act: -0.1700

Data Index: 1043238 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 3.1701. Min Range: -3.1701

Max Act: 2.9966. Min Act: -0.1700

Data Index: 160593 (C4 (Web Text))

Max Activating Token Index: 850