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

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

Neuron 1129 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: 5.9199. Min Range: -5.9199

Max Act: 5.8262. Min Act: -0.1700

Data Index: 679453 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 5.9199. Min Range: -5.9199

Max Act: 5.7949. Min Act: -0.1700

Data Index: 540157 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 5.9199. Min Range: -5.9199

Max Act: 5.9199. Min Act: -0.1700

Data Index: 210197 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 5.9199. Min Range: -5.9199

Max Act: 5.8262. Min Act: -0.1700

Data Index: 190086 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 5.9199. Min Range: -5.9199

Max Act: 5.7949. Min Act: -0.1700

Data Index: 640533 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 5.9199. Min Range: -5.9199

Max Act: 5.7324. Min Act: -0.1700

Data Index: 954542 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 5.9199. Min Range: -5.9199

Max Act: 5.7012. Min Act: -0.1700

Data Index: 986468 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 5.9199. Min Range: -5.9199

Max Act: 5.7012. Min Act: -0.1700

Data Index: 1084275 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 5.9199. Min Range: -5.9199

Max Act: 5.7324. Min Act: -0.1700

Data Index: 207864 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 5.9199. Min Range: -5.9199

Max Act: 5.6387. Min Act: -0.1700

Data Index: 749542 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 5.9199. Min Range: -5.9199

Max Act: 5.6074. Min Act: -0.1700

Data Index: 96766 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 5.9199. Min Range: -5.9199

Max Act: 5.6074. Min Act: -0.1700

Data Index: 941704 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 5.9199. Min Range: -5.9199

Max Act: 5.5449. Min Act: -0.1700

Data Index: 643987 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 5.9199. Min Range: -5.9199

Max Act: 5.6387. Min Act: -0.1700

Data Index: 898612 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 5.9199. Min Range: -5.9199

Max Act: 5.6699. Min Act: -0.1700

Data Index: 487058 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 5.9199. Min Range: -5.9199

Max Act: 5.6074. Min Act: -0.1700

Data Index: 418460 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 5.9199. Min Range: -5.9199

Max Act: 5.6074. Min Act: -0.1700

Data Index: 982616 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 5.9199. Min Range: -5.9199

Max Act: 5.4824. Min Act: -0.1700

Data Index: 1202858 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 5.9199. Min Range: -5.9199

Max Act: 5.5762. Min Act: -0.1700

Data Index: 1227869 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 5.9199. Min Range: -5.9199

Max Act: 5.5762. Min Act: -0.1700

Data Index: 148209 (C4 (Web Text))

Max Activating Token Index: 232