Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 958 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.9750. Min Act: -0.1700

Data Index: 517932 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.9750. Min Act: -0.1700

Data Index: 596528 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.9125. Min Act: -0.1700

Data Index: 1149555 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.8812. Min Act: -0.1700

Data Index: 1310320 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.8812. Min Act: -0.1700

Data Index: 257558 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.7561. Min Act: -0.1700

Data Index: 612523 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.7874. Min Act: -0.1700

Data Index: 1253733 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.7561. Min Act: -0.1700

Data Index: 452307 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.7561. Min Act: -0.1700

Data Index: 338075 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.7874. Min Act: -0.1700

Data Index: 1052162 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.7561. Min Act: -0.1700

Data Index: 107951 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.7874. Min Act: -0.1700

Data Index: 14242 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.7874. Min Act: -0.1700

Data Index: 175214 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.7874. Min Act: -0.1700

Data Index: 437136 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.7561. Min Act: -0.1700

Data Index: 243296 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.7248. Min Act: -0.1700

Data Index: 334041 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.7561. Min Act: -0.1700

Data Index: 527253 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.7248. Min Act: -0.1700

Data Index: 66631 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.7248. Min Act: -0.1700

Data Index: 844575 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 3.9750. Min Range: -3.9750

Max Act: 3.7248. Min Act: -0.1700

Data Index: 565127 (C4 (Web Text))

Max Activating Token Index: 647