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

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

Neuron 392 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.2640. Min Act: -0.1700

Data Index: 34285 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.2483. Min Act: -0.1700

Data Index: 704414 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.2483. Min Act: -0.1700

Data Index: 1077861 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.2325. Min Act: -0.1700

Data Index: 876395 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.2325. Min Act: -0.1700

Data Index: 96117 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.2011. Min Act: -0.1700

Data Index: 1227561 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.1539. Min Act: -0.1700

Data Index: 907710 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.1381. Min Act: -0.1700

Data Index: 662834 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.1224. Min Act: -0.1700

Data Index: 81015 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.1224. Min Act: -0.1700

Data Index: 874407 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.1224. Min Act: -0.1700

Data Index: 1215901 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.1224. Min Act: -0.1700

Data Index: 651453 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.1224. Min Act: -0.1700

Data Index: 1290733 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.0908. Min Act: -0.1700

Data Index: 808059 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.1066. Min Act: -0.1700

Data Index: 1216656 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.0750. Min Act: -0.1700

Data Index: 1231377 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.0593. Min Act: -0.1700

Data Index: 230559 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.0593. Min Act: -0.1700

Data Index: 383878 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.0435. Min Act: -0.1700

Data Index: 888658 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 3.2640. Min Range: -3.2640

Max Act: 3.0277. Min Act: -0.1700

Data Index: 398955 (C4 (Web Text))

Max Activating Token Index: 763