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

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

Neuron 1333 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: 5.1928. Min Range: -5.1928

Max Act: 5.1928. Min Act: -0.1700

Data Index: 1050243 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 5.1928. Min Range: -5.1928

Max Act: 5.0991. Min Act: -0.1700

Data Index: 963440 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 5.1928. Min Range: -5.1928

Max Act: 5.1616. Min Act: -0.1699

Data Index: 496569 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 5.1928. Min Range: -5.1928

Max Act: 5.0991. Min Act: -0.1700

Data Index: 794097 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 5.1928. Min Range: -5.1928

Max Act: 5.0991. Min Act: -0.1700

Data Index: 1152919 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 5.1928. Min Range: -5.1928

Max Act: 5.1928. Min Act: -0.1700

Data Index: 1002705 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 5.1928. Min Range: -5.1928

Max Act: 5.1928. Min Act: -0.1700

Data Index: 1306192 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 5.1928. Min Range: -5.1928

Max Act: 5.0053. Min Act: -0.1700

Data Index: 882837 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 5.1928. Min Range: -5.1928

Max Act: 5.0991. Min Act: -0.1700

Data Index: 1159540 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 5.1928. Min Range: -5.1928

Max Act: 5.0053. Min Act: -0.1700

Data Index: 745577 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 5.1928. Min Range: -5.1928

Max Act: 5.0678. Min Act: -0.1700

Data Index: 38481 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 5.1928. Min Range: -5.1928

Max Act: 5.0366. Min Act: -0.1700

Data Index: 881287 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 5.1928. Min Range: -5.1928

Max Act: 5.0366. Min Act: -0.1700

Data Index: 376479 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 5.1928. Min Range: -5.1928

Max Act: 5.0053. Min Act: -0.1700

Data Index: 1267177 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 5.1928. Min Range: -5.1928

Max Act: 4.9741. Min Act: -0.1700

Data Index: 624219 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 5.1928. Min Range: -5.1928

Max Act: 5.0053. Min Act: -0.1700

Data Index: 437278 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 5.1928. Min Range: -5.1928

Max Act: 4.9428. Min Act: -0.1700

Data Index: 796430 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 5.1928. Min Range: -5.1928

Max Act: 4.9428. Min Act: -0.1700

Data Index: 564850 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 5.1928. Min Range: -5.1928

Max Act: 4.9428. Min Act: -0.1700

Data Index: 629346 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 5.1928. Min Range: -5.1928

Max Act: 4.9116. Min Act: -0.1698

Data Index: 120280 (C4 (Web Text))

Max Activating Token Index: 999