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

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

Neuron 110 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: 5.5928. Min Range: -5.5928

Max Act: 5.5928. Min Act: -0.1700

Data Index: 121230 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 5.5928. Min Range: -5.5928

Max Act: 5.5303. Min Act: -0.1700

Data Index: 1234490 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 5.5928. Min Range: -5.5928

Max Act: 5.4678. Min Act: -0.1700

Data Index: 528482 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 5.5928. Min Range: -5.5928

Max Act: 5.4678. Min Act: -0.1700

Data Index: 938644 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 5.5928. Min Range: -5.5928

Max Act: 5.4365. Min Act: -0.1700

Data Index: 1274883 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 5.5928. Min Range: -5.5928

Max Act: 5.3428. Min Act: -0.1700

Data Index: 360847 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 5.5928. Min Range: -5.5928

Max Act: 5.3740. Min Act: -0.1700

Data Index: 612894 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 5.5928. Min Range: -5.5928

Max Act: 5.3115. Min Act: -0.1700

Data Index: 802490 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 5.5928. Min Range: -5.5928

Max Act: 5.2490. Min Act: -0.1700

Data Index: 402379 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 5.5928. Min Range: -5.5928

Max Act: 5.3115. Min Act: -0.1700

Data Index: 905776 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 5.5928. Min Range: -5.5928

Max Act: 5.2803. Min Act: -0.1700

Data Index: 920212 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 5.5928. Min Range: -5.5928

Max Act: 5.1865. Min Act: -0.1700

Data Index: 800136 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 5.5928. Min Range: -5.5928

Max Act: 5.2490. Min Act: -0.1700

Data Index: 855266 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 5.5928. Min Range: -5.5928

Max Act: 5.1553. Min Act: -0.1700

Data Index: 1066519 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 5.5928. Min Range: -5.5928

Max Act: 5.1240. Min Act: -0.1700

Data Index: 1141499 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 5.5928. Min Range: -5.5928

Max Act: 5.1240. Min Act: -0.1700

Data Index: 480228 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 5.5928. Min Range: -5.5928

Max Act: 5.2178. Min Act: -0.1700

Data Index: 686690 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 5.5928. Min Range: -5.5928

Max Act: 5.2178. Min Act: -0.1700

Data Index: 568351 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 5.5928. Min Range: -5.5928

Max Act: 5.2803. Min Act: -0.1700

Data Index: 780429 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 5.5928. Min Range: -5.5928

Max Act: 5.1553. Min Act: -0.1700

Data Index: 905056 (C4 (Web Text))

Max Activating Token Index: 30