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

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

Neuron 719 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: 5.3620. Min Range: -5.3620

Max Act: 5.3620. Min Act: -0.1700

Data Index: 491540 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 5.3620. Min Range: -5.3620

Max Act: 5.2995. Min Act: -0.1700

Data Index: 629796 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 5.3620. Min Range: -5.3620

Max Act: 5.2058. Min Act: -0.1700

Data Index: 1291030 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 5.3620. Min Range: -5.3620

Max Act: 5.2058. Min Act: -0.1700

Data Index: 296389 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 5.3620. Min Range: -5.3620

Max Act: 5.2058. Min Act: -0.1700

Data Index: 523819 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 5.3620. Min Range: -5.3620

Max Act: 5.2058. Min Act: -0.1700

Data Index: 637682 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 5.3620. Min Range: -5.3620

Max Act: 5.1745. Min Act: -0.1700

Data Index: 11698 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 5.3620. Min Range: -5.3620

Max Act: 5.1433. Min Act: -0.1700

Data Index: 633835 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 5.3620. Min Range: -5.3620

Max Act: 5.1745. Min Act: -0.1700

Data Index: 717003 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 5.3620. Min Range: -5.3620

Max Act: 5.2370. Min Act: -0.1700

Data Index: 903965 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 5.3620. Min Range: -5.3620

Max Act: 5.1433. Min Act: -0.1700

Data Index: 632784 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 5.3620. Min Range: -5.3620

Max Act: 5.1745. Min Act: -0.1700

Data Index: 332600 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 5.3620. Min Range: -5.3620

Max Act: 5.1745. Min Act: -0.1700

Data Index: 417349 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 5.3620. Min Range: -5.3620

Max Act: 5.1745. Min Act: -0.1700

Data Index: 235859 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 5.3620. Min Range: -5.3620

Max Act: 5.1745. Min Act: -0.1700

Data Index: 297601 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 5.3620. Min Range: -5.3620

Max Act: 5.1120. Min Act: -0.1700

Data Index: 583329 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 5.3620. Min Range: -5.3620

Max Act: 5.1120. Min Act: -0.1700

Data Index: 182088 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 5.3620. Min Range: -5.3620

Max Act: 5.1120. Min Act: -0.1700

Data Index: 599934 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 5.3620. Min Range: -5.3620

Max Act: 5.1745. Min Act: -0.1700

Data Index: 665799 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 5.3620. Min Range: -5.3620

Max Act: 5.1433. Min Act: -0.1700

Data Index: 40311 (C4 (Web Text))

Max Activating Token Index: 398