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

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

Neuron 1265 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.7643. Min Act: -0.1700

Data Index: 1000513 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.6078. Min Act: -0.1700

Data Index: 570472 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.6078. Min Act: -0.1700

Data Index: 319473 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.6391. Min Act: -0.1700

Data Index: 923681 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.5452. Min Act: -0.1700

Data Index: 215140 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.5452. Min Act: -0.1700

Data Index: 1292757 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.5138. Min Act: -0.1700

Data Index: 544379 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.5138. Min Act: -0.1700

Data Index: 811113 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.5138. Min Act: -0.1700

Data Index: 1121348 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.4825. Min Act: -0.1700

Data Index: 903227 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.4825. Min Act: -0.1700

Data Index: 224029 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.4511. Min Act: -0.1700

Data Index: 274459 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.4825. Min Act: -0.1700

Data Index: 958761 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.4511. Min Act: -0.1700

Data Index: 180284 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.5138. Min Act: -0.1700

Data Index: 778355 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.4198. Min Act: -0.1700

Data Index: 1094466 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.4511. Min Act: -0.1700

Data Index: 172407 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.4825. Min Act: -0.1700

Data Index: 52442 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.4511. Min Act: -0.1700

Data Index: 582054 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 3.7643. Min Range: -3.7643

Max Act: 3.4825. Min Act: -0.1700

Data Index: 25374 (C4 (Web Text))

Max Activating Token Index: 879