Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1252 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.4101. Min Range: -5.4101

Max Act: 5.4101. Min Act: -0.1700

Data Index: 1155624 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 5.4101. Min Range: -5.4101

Max Act: 5.2539. Min Act: -0.1700

Data Index: 1205606 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 5.4101. Min Range: -5.4101

Max Act: 5.1914. Min Act: -0.1700

Data Index: 885507 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 5.4101. Min Range: -5.4101

Max Act: 4.9414. Min Act: -0.1700

Data Index: 809512 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 5.4101. Min Range: -5.4101

Max Act: 5.0039. Min Act: -0.1700

Data Index: 160073 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 5.4101. Min Range: -5.4101

Max Act: 4.9101. Min Act: -0.1700

Data Index: 1321777 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 5.4101. Min Range: -5.4101

Max Act: 4.8789. Min Act: -0.1700

Data Index: 797911 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 5.4101. Min Range: -5.4101

Max Act: 4.8164. Min Act: -0.1700

Data Index: 372193 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 5.4101. Min Range: -5.4101

Max Act: 4.8164. Min Act: -0.1700

Data Index: 49461 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 5.4101. Min Range: -5.4101

Max Act: 4.7851. Min Act: -0.1700

Data Index: 856821 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 5.4101. Min Range: -5.4101

Max Act: 4.7226. Min Act: -0.1700

Data Index: 1558226 (Python Code)

Max Activating Token Index: 377

Text #11

Max Range: 5.4101. Min Range: -5.4101

Max Act: 4.7226. Min Act: -0.1700

Data Index: 272388 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 5.4101. Min Range: -5.4101

Max Act: 4.7851. Min Act: -0.1700

Data Index: 1226401 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 5.4101. Min Range: -5.4101

Max Act: 4.7851. Min Act: -0.1700

Data Index: 1075927 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 5.4101. Min Range: -5.4101

Max Act: 4.7539. Min Act: -0.1700

Data Index: 1194708 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 5.4101. Min Range: -5.4101

Max Act: 4.7226. Min Act: -0.1700

Data Index: 872517 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 5.4101. Min Range: -5.4101

Max Act: 4.7226. Min Act: -0.1700

Data Index: 1067260 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 5.4101. Min Range: -5.4101

Max Act: 4.6914. Min Act: -0.1700

Data Index: 139781 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 5.4101. Min Range: -5.4101

Max Act: 4.7226. Min Act: -0.1700

Data Index: 686515 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 5.4101. Min Range: -5.4101

Max Act: 4.6289. Min Act: -0.1700

Data Index: 964168 (C4 (Web Text))

Max Activating Token Index: 274