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

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

Neuron 659 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.3390. Min Act: -0.1700

Data Index: 1106881 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.2452. Min Act: -0.1700

Data Index: 1027510 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.2452. Min Act: -0.1700

Data Index: 1357220 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.2452. Min Act: -0.1700

Data Index: 1180135 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1515. Min Act: -0.1700

Data Index: 9117 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1827. Min Act: -0.1700

Data Index: 82016 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1202. Min Act: -0.1700

Data Index: 710658 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1827. Min Act: -0.1700

Data Index: 72820 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0890. Min Act: -0.1700

Data Index: 984775 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0577. Min Act: -0.1700

Data Index: 557035 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0577. Min Act: -0.1700

Data Index: 572027 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9952. Min Act: -0.1700

Data Index: 743487 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0577. Min Act: -0.1700

Data Index: 234800 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9952. Min Act: -0.1700

Data Index: 458008 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0265. Min Act: -0.1700

Data Index: 787619 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9952. Min Act: -0.1700

Data Index: 608632 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0265. Min Act: -0.1700

Data Index: 1323889 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9015. Min Act: -0.1700

Data Index: 249249 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9640. Min Act: -0.1700

Data Index: 683606 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9015. Min Act: -0.1700

Data Index: 327843 (C4 (Web Text))

Max Activating Token Index: 940