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

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

Neuron 299 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1931. Min Range: -6.1931

Max Act: 6.1931. Min Act: -0.1700

Data Index: 406680 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 6.1931. Min Range: -6.1931

Max Act: 6.1619. Min Act: -0.1700

Data Index: 250483 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 6.1931. Min Range: -6.1931

Max Act: 6.1931. Min Act: -0.1700

Data Index: 302811 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 6.1931. Min Range: -6.1931

Max Act: 6.1306. Min Act: -0.1700

Data Index: 133045 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 6.1931. Min Range: -6.1931

Max Act: 6.0369. Min Act: -0.1700

Data Index: 610251 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 6.1931. Min Range: -6.1931

Max Act: 5.8806. Min Act: -0.1700

Data Index: 361206 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 6.1931. Min Range: -6.1931

Max Act: 5.9431. Min Act: -0.1700

Data Index: 454714 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 6.1931. Min Range: -6.1931

Max Act: 5.9744. Min Act: -0.1700

Data Index: 670358 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 6.1931. Min Range: -6.1931

Max Act: 5.8494. Min Act: -0.1700

Data Index: 462462 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 6.1931. Min Range: -6.1931

Max Act: 5.9431. Min Act: -0.1700

Data Index: 1207206 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 6.1931. Min Range: -6.1931

Max Act: 5.8806. Min Act: -0.1700

Data Index: 445517 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 6.1931. Min Range: -6.1931

Max Act: 5.8806. Min Act: -0.1700

Data Index: 514041 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 6.1931. Min Range: -6.1931

Max Act: 5.8806. Min Act: -0.1700

Data Index: 1285681 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 6.1931. Min Range: -6.1931

Max Act: 5.8650. Min Act: -0.1700

Data Index: 1300719 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 6.1931. Min Range: -6.1931

Max Act: 5.8806. Min Act: -0.1700

Data Index: 115462 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 6.1931. Min Range: -6.1931

Max Act: 5.8806. Min Act: -0.1700

Data Index: 524952 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 6.1931. Min Range: -6.1931

Max Act: 5.8494. Min Act: -0.1700

Data Index: 411582 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 6.1931. Min Range: -6.1931

Max Act: 5.9431. Min Act: -0.1700

Data Index: 1270247 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 6.1931. Min Range: -6.1931

Max Act: 5.8650. Min Act: -0.1700

Data Index: 322354 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 6.1931. Min Range: -6.1931

Max Act: 5.8338. Min Act: -0.1700

Data Index: 851044 (C4 (Web Text))

Max Activating Token Index: 840