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

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

Neuron 1523 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: 5.5531. Min Range: -5.5531

Max Act: 5.5218. Min Act: -0.1700

Data Index: 1248679 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.5218. Min Act: -0.1700

Data Index: 1093039 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.5531. Min Act: -0.1700

Data Index: 1003295 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.4281. Min Act: -0.1700

Data Index: 615696 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.3343. Min Act: -0.1700

Data Index: 1311919 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.3656. Min Act: -0.1700

Data Index: 195775 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.3343. Min Act: -0.1700

Data Index: 973987 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.3343. Min Act: -0.1700

Data Index: 1200388 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.3343. Min Act: -0.1700

Data Index: 1272684 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.2406. Min Act: -0.1700

Data Index: 549628 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.3031. Min Act: -0.1700

Data Index: 999703 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.2406. Min Act: -0.1700

Data Index: 448016 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.2718. Min Act: -0.1700

Data Index: 477955 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.2406. Min Act: -0.1700

Data Index: 187308 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.2093. Min Act: -0.1700

Data Index: 948779 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.2093. Min Act: -0.1700

Data Index: 1307961 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.2093. Min Act: -0.1700

Data Index: 158033 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.2093. Min Act: -0.1700

Data Index: 259086 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.1781. Min Act: -0.1700

Data Index: 1067474 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 5.5531. Min Range: -5.5531

Max Act: 5.1781. Min Act: -0.1700

Data Index: 1289485 (C4 (Web Text))

Max Activating Token Index: 412