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

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

Neuron 1273 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: 3.9903. Min Range: -3.9903

Max Act: 3.9903. Min Act: -0.1700

Data Index: 1257546 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 3.9903. Min Range: -3.9903

Max Act: 3.7401. Min Act: -0.1700

Data Index: 227104 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 3.9903. Min Range: -3.9903

Max Act: 3.6619. Min Act: -0.1700

Data Index: 78049 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 3.9903. Min Range: -3.9903

Max Act: 3.5836. Min Act: -0.1700

Data Index: 995173 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 3.9903. Min Range: -3.9903

Max Act: 3.5679. Min Act: -0.1700

Data Index: 70780 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 3.9903. Min Range: -3.9903

Max Act: 3.4896. Min Act: -0.1700

Data Index: 821851 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 3.9903. Min Range: -3.9903

Max Act: 3.5053. Min Act: -0.1700

Data Index: 670667 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 3.9903. Min Range: -3.9903

Max Act: 3.5209. Min Act: -0.1700

Data Index: 1196392 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 3.9903. Min Range: -3.9903

Max Act: 3.4583. Min Act: -0.1700

Data Index: 742006 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 3.9903. Min Range: -3.9903

Max Act: 3.4426. Min Act: -0.1700

Data Index: 1354620 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 3.9903. Min Range: -3.9903

Max Act: 3.4269. Min Act: -0.1700

Data Index: 467327 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 3.9903. Min Range: -3.9903

Max Act: 3.4269. Min Act: -0.1700

Data Index: 886201 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 3.9903. Min Range: -3.9903

Max Act: 3.3955. Min Act: -0.1700

Data Index: 469381 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 3.9903. Min Range: -3.9903

Max Act: 3.4112. Min Act: -0.1700

Data Index: 1311391 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 3.9903. Min Range: -3.9903

Max Act: 3.3642. Min Act: -0.1700

Data Index: 270676 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 3.9903. Min Range: -3.9903

Max Act: 3.3955. Min Act: -0.1700

Data Index: 347696 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 3.9903. Min Range: -3.9903

Max Act: 3.3955. Min Act: -0.1700

Data Index: 530972 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 3.9903. Min Range: -3.9903

Max Act: 3.3642. Min Act: -0.1700

Data Index: 874525 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 3.9903. Min Range: -3.9903

Max Act: 3.3798. Min Act: -0.1700

Data Index: 380925 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 3.9903. Min Range: -3.9903

Max Act: 3.3798. Min Act: -0.1700

Data Index: 213285 (C4 (Web Text))

Max Activating Token Index: 25