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

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

Neuron 1840 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.7025. Min Act: -0.1700

Data Index: 710588 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.7182. Min Act: -0.1700

Data Index: 405738 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.7025. Min Act: -0.1700

Data Index: 1288536 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1219298 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.6243. Min Act: -0.1700

Data Index: 1148856 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.6399. Min Act: -0.1700

Data Index: 805853 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.6086. Min Act: -0.1700

Data Index: 973780 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.6086. Min Act: -0.1700

Data Index: 1260370 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.5773. Min Act: -0.1700

Data Index: 233246 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.5773. Min Act: -0.1700

Data Index: 1130915 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.6086. Min Act: -0.1700

Data Index: 642234 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.5773. Min Act: -0.1700

Data Index: 1344728 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.5930. Min Act: -0.1700

Data Index: 1346032 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.5460. Min Act: -0.1700

Data Index: 64569 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.5930. Min Act: -0.1700

Data Index: 63659 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.5930. Min Act: -0.1700

Data Index: 1001092 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.5773. Min Act: -0.1700

Data Index: 39029 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.5930. Min Act: -0.1700

Data Index: 662280 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.5773. Min Act: -0.1700

Data Index: 1045678 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 3.7182. Min Range: -3.7182

Max Act: 3.5930. Min Act: -0.1700

Data Index: 204211 (C4 (Web Text))

Max Activating Token Index: 438