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

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

Neuron 920 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: 5.5704. Min Range: -5.5704

Max Act: 5.5704. Min Act: -0.1700

Data Index: 1354764 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 5.5704. Min Range: -5.5704

Max Act: 5.4454. Min Act: -0.1700

Data Index: 1342536 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 5.5704. Min Range: -5.5704

Max Act: 5.5079. Min Act: -0.1700

Data Index: 253299 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 5.5704. Min Range: -5.5704

Max Act: 5.4454. Min Act: -0.1700

Data Index: 415252 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 5.5704. Min Range: -5.5704

Max Act: 5.4454. Min Act: -0.1700

Data Index: 928882 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 5.5704. Min Range: -5.5704

Max Act: 5.4454. Min Act: -0.1700

Data Index: 683386 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 5.5704. Min Range: -5.5704

Max Act: 5.4454. Min Act: -0.1700

Data Index: 510393 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 5.5704. Min Range: -5.5704

Max Act: 5.4454. Min Act: -0.1700

Data Index: 715132 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 5.5704. Min Range: -5.5704

Max Act: 5.4142. Min Act: -0.1700

Data Index: 980503 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 5.5704. Min Range: -5.5704

Max Act: 5.4454. Min Act: -0.1700

Data Index: 566645 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 5.5704. Min Range: -5.5704

Max Act: 5.4454. Min Act: -0.1700

Data Index: 81364 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 5.5704. Min Range: -5.5704

Max Act: 5.4767. Min Act: -0.1700

Data Index: 1203622 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 5.5704. Min Range: -5.5704

Max Act: 5.3829. Min Act: -0.1700

Data Index: 515289 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 5.5704. Min Range: -5.5704

Max Act: 5.3829. Min Act: -0.1700

Data Index: 970137 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 5.5704. Min Range: -5.5704

Max Act: 5.4454. Min Act: -0.1700

Data Index: 330733 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 5.5704. Min Range: -5.5704

Max Act: 5.3829. Min Act: -0.1700

Data Index: 936919 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 5.5704. Min Range: -5.5704

Max Act: 5.3829. Min Act: -0.1700

Data Index: 121549 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 5.5704. Min Range: -5.5704

Max Act: 5.3829. Min Act: -0.1700

Data Index: 218765 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 5.5704. Min Range: -5.5704

Max Act: 5.3829. Min Act: -0.1700

Data Index: 662861 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 5.5704. Min Range: -5.5704

Max Act: 5.3204. Min Act: -0.1700

Data Index: 1039302 (C4 (Web Text))

Max Activating Token Index: 632