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

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

Neuron 1367 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: 5.7149. Min Range: -5.7149

Max Act: 5.7149. Min Act: -0.1700

Data Index: 795510 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 5.7149. Min Range: -5.7149

Max Act: 5.6836. Min Act: -0.1700

Data Index: 1035179 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 5.7149. Min Range: -5.7149

Max Act: 5.5899. Min Act: -0.1700

Data Index: 93636 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 5.7149. Min Range: -5.7149

Max Act: 5.4961. Min Act: -0.1700

Data Index: 786465 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 5.7149. Min Range: -5.7149

Max Act: 5.5274. Min Act: -0.1700

Data Index: 1175016 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 5.7149. Min Range: -5.7149

Max Act: 5.4961. Min Act: -0.1700

Data Index: 1226748 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 5.7149. Min Range: -5.7149

Max Act: 5.4336. Min Act: -0.1700

Data Index: 569534 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 5.7149. Min Range: -5.7149

Max Act: 5.4961. Min Act: -0.1700

Data Index: 991790 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 5.7149. Min Range: -5.7149

Max Act: 5.4961. Min Act: -0.1700

Data Index: 635413 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 5.7149. Min Range: -5.7149

Max Act: 5.4961. Min Act: -0.1700

Data Index: 758880 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 5.7149. Min Range: -5.7149

Max Act: 5.4649. Min Act: -0.1700

Data Index: 1045818 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 5.7149. Min Range: -5.7149

Max Act: 5.4649. Min Act: -0.1700

Data Index: 1031280 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 5.7149. Min Range: -5.7149

Max Act: 5.4649. Min Act: -0.1700

Data Index: 3258 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 5.7149. Min Range: -5.7149

Max Act: 5.4961. Min Act: -0.1700

Data Index: 853139 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 5.7149. Min Range: -5.7149

Max Act: 5.4649. Min Act: -0.1700

Data Index: 89425 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 5.7149. Min Range: -5.7149

Max Act: 5.4336. Min Act: -0.1700

Data Index: 340701 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 5.7149. Min Range: -5.7149

Max Act: 5.4961. Min Act: -0.1700

Data Index: 995498 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 5.7149. Min Range: -5.7149

Max Act: 5.4336. Min Act: -0.1700

Data Index: 419854 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 5.7149. Min Range: -5.7149

Max Act: 5.4336. Min Act: -0.1700

Data Index: 309650 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 5.7149. Min Range: -5.7149

Max Act: 5.4336. Min Act: -0.1700

Data Index: 395329 (C4 (Web Text))

Max Activating Token Index: 99