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

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

Neuron 1855 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: 3.3010. Min Range: -3.3010

Max Act: 3.3010. Min Act: -0.1700

Data Index: 1072329 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 3.3010. Min Range: -3.3010

Max Act: 3.2539. Min Act: -0.1700

Data Index: 129313 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 3.3010. Min Range: -3.3010

Max Act: 3.1910. Min Act: -0.1700

Data Index: 588767 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 3.3010. Min Range: -3.3010

Max Act: 3.2225. Min Act: -0.1700

Data Index: 335247 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 3.3010. Min Range: -3.3010

Max Act: 3.1910. Min Act: -0.1700

Data Index: 1199840 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 3.3010. Min Range: -3.3010

Max Act: 3.1595. Min Act: -0.1700

Data Index: 815701 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 3.3010. Min Range: -3.3010

Max Act: 3.1438. Min Act: -0.1700

Data Index: 1123946 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 3.3010. Min Range: -3.3010

Max Act: 3.1280. Min Act: -0.1700

Data Index: 987556 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 3.3010. Min Range: -3.3010

Max Act: 3.1438. Min Act: -0.1700

Data Index: 650368 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 3.3010. Min Range: -3.3010

Max Act: 3.1280. Min Act: -0.1700

Data Index: 150208 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 3.3010. Min Range: -3.3010

Max Act: 3.1280. Min Act: -0.1700

Data Index: 166016 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 3.3010. Min Range: -3.3010

Max Act: 3.1595. Min Act: -0.1700

Data Index: 681684 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 3.3010. Min Range: -3.3010

Max Act: 3.1910. Min Act: -0.1700

Data Index: 990585 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 3.3010. Min Range: -3.3010

Max Act: 3.1595. Min Act: -0.1700

Data Index: 759505 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 3.3010. Min Range: -3.3010

Max Act: 3.1595. Min Act: -0.1700

Data Index: 903861 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 3.3010. Min Range: -3.3010

Max Act: 3.1280. Min Act: -0.1700

Data Index: 89184 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 3.3010. Min Range: -3.3010

Max Act: 3.1280. Min Act: -0.1700

Data Index: 1183101 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 3.3010. Min Range: -3.3010

Max Act: 3.1123. Min Act: -0.1700

Data Index: 917227 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 3.3010. Min Range: -3.3010

Max Act: 3.0807. Min Act: -0.1700

Data Index: 1128220 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 3.3010. Min Range: -3.3010

Max Act: 3.1123. Min Act: -0.1700

Data Index: 344084 (C4 (Web Text))

Max Activating Token Index: 674