Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 231 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.9833. Min Act: -0.1700

Data Index: 1320331 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.9833. Min Act: -0.1700

Data Index: 1190801 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.9520. Min Act: -0.1700

Data Index: 589580 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.9208. Min Act: -0.1700

Data Index: 921227 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.9208. Min Act: -0.1700

Data Index: 904017 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.8269. Min Act: -0.1700

Data Index: 1623374 (Python Code)

Max Activating Token Index: 1011

Text #6

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.8895. Min Act: -0.1700

Data Index: 516430 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.8895. Min Act: -0.1700

Data Index: 367545 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.7644. Min Act: -0.1700

Data Index: 439611 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.8269. Min Act: -0.1700

Data Index: 374628 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.8269. Min Act: -0.1700

Data Index: 87907 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.8895. Min Act: -0.1700

Data Index: 1221224 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.8582. Min Act: -0.1700

Data Index: 667605 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.8269. Min Act: -0.1700

Data Index: 1333437 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.7957. Min Act: -0.1700

Data Index: 35730 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.8269. Min Act: -0.1700

Data Index: 111186 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.7957. Min Act: -0.1700

Data Index: 158758 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.8269. Min Act: -0.1700

Data Index: 433353 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.7644. Min Act: -0.1700

Data Index: 370984 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 3.9833. Min Range: -3.9833

Max Act: 3.7957. Min Act: -0.1700

Data Index: 921625 (C4 (Web Text))

Max Activating Token Index: 606