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

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

Neuron 233 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: 3.6696. Min Range: -3.6696

Max Act: 3.6696. Min Act: -0.1700

Data Index: 1246058 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 3.6696. Min Range: -3.6696

Max Act: 3.6227. Min Act: -0.1700

Data Index: 299667 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 3.6696. Min Range: -3.6696

Max Act: 3.6383. Min Act: -0.1700

Data Index: 36276 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 3.6696. Min Range: -3.6696

Max Act: 3.5914. Min Act: -0.1700

Data Index: 90659 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 3.6696. Min Range: -3.6696

Max Act: 3.6070. Min Act: -0.1700

Data Index: 34572 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 3.6696. Min Range: -3.6696

Max Act: 3.6070. Min Act: -0.1700

Data Index: 872193 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 3.6696. Min Range: -3.6696

Max Act: 3.6383. Min Act: -0.1700

Data Index: 1274584 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 3.6696. Min Range: -3.6696

Max Act: 3.5600. Min Act: -0.1700

Data Index: 387031 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 3.6696. Min Range: -3.6696

Max Act: 3.5600. Min Act: -0.1700

Data Index: 954315 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 3.6696. Min Range: -3.6696

Max Act: 3.5444. Min Act: -0.1700

Data Index: 495667 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 3.6696. Min Range: -3.6696

Max Act: 3.4817. Min Act: -0.1700

Data Index: 1039796 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 3.6696. Min Range: -3.6696

Max Act: 3.4660. Min Act: -0.1700

Data Index: 1000528 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 3.6696. Min Range: -3.6696

Max Act: 3.4660. Min Act: -0.1700

Data Index: 1284738 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 3.6696. Min Range: -3.6696

Max Act: 3.4660. Min Act: -0.1700

Data Index: 1131539 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 3.6696. Min Range: -3.6696

Max Act: 3.4660. Min Act: -0.1700

Data Index: 1103801 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 3.6696. Min Range: -3.6696

Max Act: 3.4817. Min Act: -0.1700

Data Index: 97562 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 3.6696. Min Range: -3.6696

Max Act: 3.4974. Min Act: -0.1700

Data Index: 1149829 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 3.6696. Min Range: -3.6696

Max Act: 3.5131. Min Act: -0.1700

Data Index: 26190 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 3.6696. Min Range: -3.6696

Max Act: 3.4660. Min Act: -0.1700

Data Index: 305348 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 3.6696. Min Range: -3.6696

Max Act: 3.4660. Min Act: -0.1700

Data Index: 340222 (C4 (Web Text))

Max Activating Token Index: 1011