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

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

Neuron 713 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.6310. Min Act: -0.1700

Data Index: 1515281 (Python Code)

Max Activating Token Index: 950

Text #1

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.5683. Min Act: -0.1700

Data Index: 1604267 (Python Code)

Max Activating Token Index: 841

Text #2

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.4743. Min Act: -0.1700

Data Index: 1082973 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.4743. Min Act: -0.1700

Data Index: 1600445 (Python Code)

Max Activating Token Index: 445

Text #4

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.4116. Min Act: -0.1700

Data Index: 1583370 (Python Code)

Max Activating Token Index: 16

Text #5

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.4116. Min Act: -0.1700

Data Index: 1576893 (Python Code)

Max Activating Token Index: 234

Text #6

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.3802. Min Act: -0.1700

Data Index: 1633135 (Python Code)

Max Activating Token Index: 84

Text #7

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.3489. Min Act: -0.1700

Data Index: 1484509 (Python Code)

Max Activating Token Index: 1007

Text #8

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.3489. Min Act: -0.1700

Data Index: 1412218 (Python Code)

Max Activating Token Index: 219

Text #9

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.3802. Min Act: -0.1700

Data Index: 245868 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.3489. Min Act: -0.1700

Data Index: 1399551 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.3802. Min Act: -0.1700

Data Index: 1646730 (Python Code)

Max Activating Token Index: 185

Text #12

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.3175. Min Act: -0.1700

Data Index: 324221 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.2861. Min Act: -0.1700

Data Index: 1528733 (Python Code)

Max Activating Token Index: 223

Text #14

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.3175. Min Act: -0.1700

Data Index: 1603776 (Python Code)

Max Activating Token Index: 573

Text #15

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.2861. Min Act: -0.1700

Data Index: 1642081 (Python Code)

Max Activating Token Index: 898

Text #16

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.3489. Min Act: -0.1700

Data Index: 709634 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.3175. Min Act: -0.1700

Data Index: 1199131 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.3175. Min Act: -0.1700

Data Index: 1001604 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.2546. Min Act: -0.1700

Data Index: 1439308 (Python Code)

Max Activating Token Index: 180