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

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

Neuron 1685 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: 3.4539. Min Range: -3.4539

Max Act: 3.4225. Min Act: -0.1700

Data Index: 463750 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.4539. Min Act: -0.1700

Data Index: 776919 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.3911. Min Act: -0.1700

Data Index: 722096 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.3441. Min Act: -0.1700

Data Index: 834433 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.2498. Min Act: -0.1700

Data Index: 1046019 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.2184. Min Act: -0.1700

Data Index: 639118 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1554. Min Act: -0.1700

Data Index: 129745 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1869. Min Act: -0.1700

Data Index: 154093 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1712. Min Act: -0.1700

Data Index: 1071653 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1712. Min Act: -0.1700

Data Index: 1589710 (Python Code)

Max Activating Token Index: 563

Text #10

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1712. Min Act: -0.1700

Data Index: 670771 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1554. Min Act: -0.1700

Data Index: 1256484 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1554. Min Act: -0.1700

Data Index: 926417 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1082. Min Act: -0.1700

Data Index: 352970 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1712. Min Act: -0.1700

Data Index: 1199872 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1554. Min Act: -0.1700

Data Index: 599635 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1397. Min Act: -0.1700

Data Index: 776088 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1239. Min Act: -0.1700

Data Index: 701668 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1397. Min Act: -0.1700

Data Index: 1442128 (Python Code)

Max Activating Token Index: 736

Text #19

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1397. Min Act: -0.1700

Data Index: 1533911 (Python Code)

Max Activating Token Index: 360