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

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

Neuron 1325 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: 5.8436. Min Range: -5.8436

Max Act: 5.8436. Min Act: -0.1700

Data Index: 495752 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 5.8436. Min Range: -5.8436

Max Act: 5.4999. Min Act: -0.1700

Data Index: 224885 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 5.8436. Min Range: -5.8436

Max Act: 5.2811. Min Act: -0.1700

Data Index: 219719 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 5.8436. Min Range: -5.8436

Max Act: 5.2499. Min Act: -0.1700

Data Index: 504508 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 5.8436. Min Range: -5.8436

Max Act: 5.1874. Min Act: -0.1700

Data Index: 166604 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 5.8436. Min Range: -5.8436

Max Act: 5.2811. Min Act: -0.1700

Data Index: 700082 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 5.8436. Min Range: -5.8436

Max Act: 5.1561. Min Act: -0.1700

Data Index: 688762 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 5.8436. Min Range: -5.8436

Max Act: 5.1874. Min Act: -0.1700

Data Index: 448002 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 5.8436. Min Range: -5.8436

Max Act: 5.1249. Min Act: -0.1699

Data Index: 144818 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 5.8436. Min Range: -5.8436

Max Act: 5.0624. Min Act: -0.1700

Data Index: 1189301 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 5.8436. Min Range: -5.8436

Max Act: 4.9999. Min Act: -0.1700

Data Index: 110610 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 5.8436. Min Range: -5.8436

Max Act: 4.9999. Min Act: -0.1700

Data Index: 81484 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 5.8436. Min Range: -5.8436

Max Act: 4.8749. Min Act: -0.1700

Data Index: 1107028 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 5.8436. Min Range: -5.8436

Max Act: 4.9061. Min Act: -0.1700

Data Index: 1109138 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 5.8436. Min Range: -5.8436

Max Act: 4.9374. Min Act: -0.1700

Data Index: 1211412 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 5.8436. Min Range: -5.8436

Max Act: 4.8749. Min Act: -0.1700

Data Index: 7218 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 5.8436. Min Range: -5.8436

Max Act: 4.8749. Min Act: -0.1700

Data Index: 842800 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 5.8436. Min Range: -5.8436

Max Act: 4.8749. Min Act: -0.1700

Data Index: 444226 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 5.8436. Min Range: -5.8436

Max Act: 4.9061. Min Act: -0.1700

Data Index: 129186 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 5.8436. Min Range: -5.8436

Max Act: 4.9061. Min Act: -0.1700

Data Index: 339920 (C4 (Web Text))

Max Activating Token Index: 583