Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1785 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.2200. Min Act: -0.1700

Data Index: 455909 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.2357. Min Act: -0.1700

Data Index: 352049 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.1885. Min Act: -0.1700

Data Index: 291765 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.1570. Min Act: -0.1700

Data Index: 966659 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.1255. Min Act: -0.1700

Data Index: 576274 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.1255. Min Act: -0.1700

Data Index: 502913 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.1255. Min Act: -0.1700

Data Index: 260517 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.1097. Min Act: -0.1700

Data Index: 326541 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.1255. Min Act: -0.1700

Data Index: 969157 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.0940. Min Act: -0.1700

Data Index: 500077 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.0782. Min Act: -0.1700

Data Index: 446921 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.0940. Min Act: -0.1700

Data Index: 654119 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.0624. Min Act: -0.1700

Data Index: 891709 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.0940. Min Act: -0.1700

Data Index: 499631 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.0466. Min Act: -0.1700

Data Index: 1514732 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.0624. Min Act: -0.1700

Data Index: 310459 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.0466. Min Act: -0.1700

Data Index: 1252275 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.0466. Min Act: -0.1700

Data Index: 1065973 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.0466. Min Act: -0.1700

Data Index: 1238682 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.2357. Min Range: -3.2357

Max Act: 3.0466. Min Act: -0.1700

Data Index: 536848 (C4 (Web Text))

Max Activating Token Index: 735