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

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

Neuron 1622 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: 4.5213. Min Range: -4.5213

Max Act: 4.5213. Min Act: -0.1700

Data Index: 212405 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.5213. Min Range: -4.5213

Max Act: 4.5213. Min Act: -0.1700

Data Index: 632102 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.5213. Min Range: -4.5213

Max Act: 4.2713. Min Act: -0.1700

Data Index: 146619 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.5213. Min Range: -4.5213

Max Act: 4.1462. Min Act: -0.1700

Data Index: 272591 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.5213. Min Range: -4.5213

Max Act: 4.1462. Min Act: -0.1700

Data Index: 96388 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 4.5213. Min Range: -4.5213

Max Act: 3.8648. Min Act: -0.1700

Data Index: 500649 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.5213. Min Range: -4.5213

Max Act: 4.0525. Min Act: -0.1700

Data Index: 616673 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 4.5213. Min Range: -4.5213

Max Act: 3.8648. Min Act: -0.1700

Data Index: 729773 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 4.5213. Min Range: -4.5213

Max Act: 3.8336. Min Act: -0.1700

Data Index: 1317155 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 4.5213. Min Range: -4.5213

Max Act: 3.8336. Min Act: -0.1700

Data Index: 468788 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.5213. Min Range: -4.5213

Max Act: 3.7084. Min Act: -0.1700

Data Index: 951288 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 4.5213. Min Range: -4.5213

Max Act: 3.7710. Min Act: -0.1700

Data Index: 423693 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 4.5213. Min Range: -4.5213

Max Act: 3.7710. Min Act: -0.1700

Data Index: 751457 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 4.5213. Min Range: -4.5213

Max Act: 3.7710. Min Act: -0.1700

Data Index: 525682 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 4.5213. Min Range: -4.5213

Max Act: 3.6771. Min Act: -0.1700

Data Index: 1009369 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 4.5213. Min Range: -4.5213

Max Act: 3.8023. Min Act: -0.1700

Data Index: 1159320 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 4.5213. Min Range: -4.5213

Max Act: 3.6458. Min Act: -0.1700

Data Index: 571547 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 4.5213. Min Range: -4.5213

Max Act: 3.7710. Min Act: -0.1700

Data Index: 102565 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 4.5213. Min Range: -4.5213

Max Act: 3.6771. Min Act: -0.1700

Data Index: 353852 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 4.5213. Min Range: -4.5213

Max Act: 3.7397. Min Act: -0.1700

Data Index: 392260 (C4 (Web Text))

Max Activating Token Index: 279