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

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

Neuron 1835 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.3832. Min Act: -0.1700

Data Index: 795823 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.2576. Min Act: -0.1700

Data Index: 1180672 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.2576. Min Act: -0.1700

Data Index: 676248 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.2262. Min Act: -0.1700

Data Index: 950233 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.2262. Min Act: -0.1700

Data Index: 1299204 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.2104. Min Act: -0.1700

Data Index: 1185576 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.1947. Min Act: -0.1700

Data Index: 672674 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.1947. Min Act: -0.1700

Data Index: 376726 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.1790. Min Act: -0.1700

Data Index: 46402 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.2104. Min Act: -0.1700

Data Index: 112931 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.1947. Min Act: -0.1700

Data Index: 504007 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.2104. Min Act: -0.1700

Data Index: 608832 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.1632. Min Act: -0.1700

Data Index: 200094 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.1632. Min Act: -0.1700

Data Index: 1255717 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.1475. Min Act: -0.1700

Data Index: 588654 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.1317. Min Act: -0.1700

Data Index: 313121 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.1317. Min Act: -0.1700

Data Index: 206418 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.1160. Min Act: -0.1700

Data Index: 905702 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.1317. Min Act: -0.1700

Data Index: 81992 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 3.3832. Min Range: -3.3832

Max Act: 3.1317. Min Act: -0.1700

Data Index: 395074 (C4 (Web Text))

Max Activating Token Index: 615