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

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

Neuron 1428 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: 5.9172. Min Range: -5.9172

Max Act: 5.9172. Min Act: -0.1700

Data Index: 406197 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 5.9172. Min Range: -5.9172

Max Act: 5.7609. Min Act: -0.1700

Data Index: 1128370 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 5.9172. Min Range: -5.9172

Max Act: 5.7922. Min Act: -0.1700

Data Index: 1082610 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 5.9172. Min Range: -5.9172

Max Act: 5.6984. Min Act: -0.1700

Data Index: 568535 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 5.9172. Min Range: -5.9172

Max Act: 5.6984. Min Act: -0.1700

Data Index: 799993 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 5.9172. Min Range: -5.9172

Max Act: 5.6672. Min Act: -0.1700

Data Index: 234448 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 5.9172. Min Range: -5.9172

Max Act: 5.7297. Min Act: -0.1700

Data Index: 266363 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 5.9172. Min Range: -5.9172

Max Act: 5.6984. Min Act: -0.1700

Data Index: 63569 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 5.9172. Min Range: -5.9172

Max Act: 5.6984. Min Act: -0.1700

Data Index: 980995 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 5.9172. Min Range: -5.9172

Max Act: 5.6672. Min Act: -0.1700

Data Index: 313744 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 5.9172. Min Range: -5.9172

Max Act: 5.6359. Min Act: -0.1700

Data Index: 413314 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 5.9172. Min Range: -5.9172

Max Act: 5.6672. Min Act: -0.1700

Data Index: 543550 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 5.9172. Min Range: -5.9172

Max Act: 5.6359. Min Act: -0.1700

Data Index: 756497 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 5.9172. Min Range: -5.9172

Max Act: 5.6359. Min Act: -0.1700

Data Index: 348571 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 5.9172. Min Range: -5.9172

Max Act: 5.5734. Min Act: -0.1700

Data Index: 693642 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 5.9172. Min Range: -5.9172

Max Act: 5.6672. Min Act: -0.1700

Data Index: 538562 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 5.9172. Min Range: -5.9172

Max Act: 5.5734. Min Act: -0.1700

Data Index: 372423 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 5.9172. Min Range: -5.9172

Max Act: 5.6672. Min Act: -0.1700

Data Index: 46002 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 5.9172. Min Range: -5.9172

Max Act: 5.6359. Min Act: -0.1700

Data Index: 224967 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 5.9172. Min Range: -5.9172

Max Act: 5.6359. Min Act: -0.1700

Data Index: 268518 (C4 (Web Text))

Max Activating Token Index: 659