Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 850 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.3812. Min Range: -5.3812

Max Act: 5.3812. Min Act: -0.1700

Data Index: 961552 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 5.3812. Min Range: -5.3812

Max Act: 5.2249. Min Act: -0.1700

Data Index: 532474 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 5.3812. Min Range: -5.3812

Max Act: 5.1312. Min Act: -0.1700

Data Index: 971239 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 5.3812. Min Range: -5.3812

Max Act: 5.0062. Min Act: -0.1700

Data Index: 388368 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 5.3812. Min Range: -5.3812

Max Act: 4.9437. Min Act: -0.1693

Data Index: 459344 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 5.3812. Min Range: -5.3812

Max Act: 4.9124. Min Act: -0.1700

Data Index: 299167 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 5.3812. Min Range: -5.3812

Max Act: 4.8812. Min Act: -0.1700

Data Index: 1050317 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 5.3812. Min Range: -5.3812

Max Act: 4.9124. Min Act: -0.1700

Data Index: 229323 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 5.3812. Min Range: -5.3812

Max Act: 4.8812. Min Act: -0.1700

Data Index: 1247346 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 5.3812. Min Range: -5.3812

Max Act: 4.8499. Min Act: -0.1698

Data Index: 1071178 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 5.3812. Min Range: -5.3812

Max Act: 4.8499. Min Act: -0.1700

Data Index: 535155 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 5.3812. Min Range: -5.3812

Max Act: 4.8499. Min Act: -0.1700

Data Index: 696585 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 5.3812. Min Range: -5.3812

Max Act: 4.8187. Min Act: -0.1700

Data Index: 854272 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 5.3812. Min Range: -5.3812

Max Act: 4.7874. Min Act: -0.1700

Data Index: 1179029 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 5.3812. Min Range: -5.3812

Max Act: 4.7874. Min Act: -0.1699

Data Index: 1250273 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 5.3812. Min Range: -5.3812

Max Act: 4.7874. Min Act: -0.1700

Data Index: 982519 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 5.3812. Min Range: -5.3812

Max Act: 4.7562. Min Act: -0.1700

Data Index: 336366 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 5.3812. Min Range: -5.3812

Max Act: 4.7562. Min Act: -0.1700

Data Index: 485480 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 5.3812. Min Range: -5.3812

Max Act: 4.7874. Min Act: -0.1700

Data Index: 29088 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 5.3812. Min Range: -5.3812

Max Act: 4.6937. Min Act: -0.1700

Data Index: 1018672 (C4 (Web Text))

Max Activating Token Index: 241