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

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

Neuron 1028 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: 3.6179. Min Range: -3.6179

Max Act: 3.6179. Min Act: -0.1700

Data Index: 1343256 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.6023. Min Act: -0.1700

Data Index: 659789 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5553. Min Act: -0.1700

Data Index: 1197736 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5866. Min Act: -0.1700

Data Index: 752876 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5553. Min Act: -0.1700

Data Index: 659672 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5709. Min Act: -0.1700

Data Index: 293916 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5709. Min Act: -0.1700

Data Index: 748019 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5866. Min Act: -0.1700

Data Index: 581425 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.4926. Min Act: -0.1700

Data Index: 858082 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5709. Min Act: -0.1700

Data Index: 550521 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5083. Min Act: -0.1700

Data Index: 1281753 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5083. Min Act: -0.1700

Data Index: 1350526 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.4769. Min Act: -0.1700

Data Index: 399169 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.4926. Min Act: -0.1700

Data Index: 119341 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.4926. Min Act: -0.1700

Data Index: 39365 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.4926. Min Act: -0.1700

Data Index: 513595 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.4769. Min Act: -0.1700

Data Index: 135610 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.4926. Min Act: -0.1700

Data Index: 1063182 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.4926. Min Act: -0.1700

Data Index: 1333374 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.4926. Min Act: -0.1700

Data Index: 1200603 (C4 (Web Text))

Max Activating Token Index: 811