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

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

Neuron 1885 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: 4.1514. Min Range: -4.1514

Max Act: 4.1514. Min Act: -0.1700

Data Index: 1213864 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 4.1514. Min Range: -4.1514

Max Act: 4.0888. Min Act: -0.1700

Data Index: 110253 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 4.1514. Min Range: -4.1514

Max Act: 3.9951. Min Act: -0.1700

Data Index: 777384 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 4.1514. Min Range: -4.1514

Max Act: 4.0107. Min Act: -0.1700

Data Index: 15616 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 4.1514. Min Range: -4.1514

Max Act: 3.9325. Min Act: -0.1700

Data Index: 1261848 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 4.1514. Min Range: -4.1514

Max Act: 3.9013. Min Act: -0.1700

Data Index: 67528 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 4.1514. Min Range: -4.1514

Max Act: 3.9013. Min Act: -0.1700

Data Index: 1144513 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 4.1514. Min Range: -4.1514

Max Act: 3.8856. Min Act: -0.1700

Data Index: 417124 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 4.1514. Min Range: -4.1514

Max Act: 3.9169. Min Act: -0.1700

Data Index: 19249 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 4.1514. Min Range: -4.1514

Max Act: 3.8856. Min Act: -0.1700

Data Index: 917402 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 4.1514. Min Range: -4.1514

Max Act: 3.8700. Min Act: -0.1700

Data Index: 1446226 (Python Code)

Max Activating Token Index: 560

Text #11

Max Range: 4.1514. Min Range: -4.1514

Max Act: 3.8387. Min Act: -0.1700

Data Index: 1487634 (Python Code)

Max Activating Token Index: 109

Text #12

Max Range: 4.1514. Min Range: -4.1514

Max Act: 3.8543. Min Act: -0.1700

Data Index: 1200393 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 4.1514. Min Range: -4.1514

Max Act: 3.8543. Min Act: -0.1700

Data Index: 739922 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 4.1514. Min Range: -4.1514

Max Act: 3.8231. Min Act: -0.1700

Data Index: 794912 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 4.1514. Min Range: -4.1514

Max Act: 3.8700. Min Act: -0.1700

Data Index: 79627 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 4.1514. Min Range: -4.1514

Max Act: 3.8231. Min Act: -0.1700

Data Index: 148426 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 4.1514. Min Range: -4.1514

Max Act: 3.8231. Min Act: -0.1700

Data Index: 710550 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 4.1514. Min Range: -4.1514

Max Act: 3.7918. Min Act: -0.1700

Data Index: 452777 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 4.1514. Min Range: -4.1514

Max Act: 3.7918. Min Act: -0.1700

Data Index: 63589 (C4 (Web Text))

Max Activating Token Index: 787