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

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

Neuron 1815 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: 3.4215. Min Range: -3.4215

Max Act: 3.4215. Min Act: -0.1700

Data Index: 52570 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 3.4215. Min Range: -3.4215

Max Act: 3.3116. Min Act: -0.1700

Data Index: 1258169 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 3.4215. Min Range: -3.4215

Max Act: 3.3116. Min Act: -0.1700

Data Index: 464377 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 3.4215. Min Range: -3.4215

Max Act: 3.2488. Min Act: -0.1700

Data Index: 1185047 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 3.4215. Min Range: -3.4215

Max Act: 3.2959. Min Act: -0.1700

Data Index: 775033 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 3.4215. Min Range: -3.4215

Max Act: 3.2645. Min Act: -0.1700

Data Index: 776017 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 3.4215. Min Range: -3.4215

Max Act: 3.2959. Min Act: -0.1700

Data Index: 584548 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 3.4215. Min Range: -3.4215

Max Act: 3.2488. Min Act: -0.1700

Data Index: 137329 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 3.4215. Min Range: -3.4215

Max Act: 3.2173. Min Act: -0.1700

Data Index: 1117426 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 3.4215. Min Range: -3.4215

Max Act: 3.2016. Min Act: -0.1700

Data Index: 856384 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 3.4215. Min Range: -3.4215

Max Act: 3.1701. Min Act: -0.1700

Data Index: 943963 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 3.4215. Min Range: -3.4215

Max Act: 3.1859. Min Act: -0.1700

Data Index: 872453 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 3.4215. Min Range: -3.4215

Max Act: 3.1701. Min Act: -0.1700

Data Index: 585452 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 3.4215. Min Range: -3.4215

Max Act: 3.0913. Min Act: -0.1700

Data Index: 475521 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 3.4215. Min Range: -3.4215

Max Act: 3.1544. Min Act: -0.1700

Data Index: 918179 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 3.4215. Min Range: -3.4215

Max Act: 3.1386. Min Act: -0.1700

Data Index: 1173574 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 3.4215. Min Range: -3.4215

Max Act: 3.1859. Min Act: -0.1700

Data Index: 1276510 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 3.4215. Min Range: -3.4215

Max Act: 3.1229. Min Act: -0.1700

Data Index: 607110 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 3.4215. Min Range: -3.4215

Max Act: 3.1229. Min Act: -0.1700

Data Index: 491711 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 3.4215. Min Range: -3.4215

Max Act: 3.1544. Min Act: -0.1700

Data Index: 743998 (C4 (Web Text))

Max Activating Token Index: 207