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

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

Neuron 1347 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1455. Min Range: -4.1455

Max Act: 4.1455. Min Act: -0.1700

Data Index: 453595 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 4.1455. Min Range: -4.1455

Max Act: 4.0830. Min Act: -0.1700

Data Index: 579946 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 4.1455. Min Range: -4.1455

Max Act: 4.0517. Min Act: -0.1700

Data Index: 248660 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 4.1455. Min Range: -4.1455

Max Act: 3.9892. Min Act: -0.1700

Data Index: 1274034 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 4.1455. Min Range: -4.1455

Max Act: 3.9892. Min Act: -0.1700

Data Index: 1184694 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 4.1455. Min Range: -4.1455

Max Act: 3.9892. Min Act: -0.1700

Data Index: 1099235 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 4.1455. Min Range: -4.1455

Max Act: 3.8954. Min Act: -0.1700

Data Index: 775373 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 4.1455. Min Range: -4.1455

Max Act: 3.8641. Min Act: -0.1700

Data Index: 1109814 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 4.1455. Min Range: -4.1455

Max Act: 3.8485. Min Act: -0.1700

Data Index: 349468 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 4.1455. Min Range: -4.1455

Max Act: 3.8172. Min Act: -0.1700

Data Index: 529176 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 4.1455. Min Range: -4.1455

Max Act: 3.7390. Min Act: -0.1700

Data Index: 114214 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 4.1455. Min Range: -4.1455

Max Act: 3.7546. Min Act: -0.1700

Data Index: 1143517 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 4.1455. Min Range: -4.1455

Max Act: 3.7233. Min Act: -0.1700

Data Index: 1017415 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 4.1455. Min Range: -4.1455

Max Act: 3.7390. Min Act: -0.1700

Data Index: 277538 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 4.1455. Min Range: -4.1455

Max Act: 3.7390. Min Act: -0.1700

Data Index: 1292951 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 4.1455. Min Range: -4.1455

Max Act: 3.6920. Min Act: -0.1700

Data Index: 1247957 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 4.1455. Min Range: -4.1455

Max Act: 3.7233. Min Act: -0.1700

Data Index: 230984 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 4.1455. Min Range: -4.1455

Max Act: 3.6920. Min Act: -0.1700

Data Index: 882338 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 4.1455. Min Range: -4.1455

Max Act: 3.6451. Min Act: -0.1700

Data Index: 171022 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 4.1455. Min Range: -4.1455

Max Act: 3.6451. Min Act: -0.1700

Data Index: 572430 (C4 (Web Text))

Max Activating Token Index: 302