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

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

Neuron 788 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: 5.9969. Min Range: -5.9969

Max Act: 5.9969. Min Act: -0.1700

Data Index: 1198539 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 5.9969. Min Range: -5.9969

Max Act: 5.9344. Min Act: -0.1700

Data Index: 238013 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 5.9969. Min Range: -5.9969

Max Act: 5.9344. Min Act: -0.1700

Data Index: 1180325 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 5.9969. Min Range: -5.9969

Max Act: 5.7157. Min Act: -0.1700

Data Index: 976096 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 5.9969. Min Range: -5.9969

Max Act: 5.7157. Min Act: -0.1700

Data Index: 713990 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 5.9969. Min Range: -5.9969

Max Act: 5.6844. Min Act: -0.1700

Data Index: 667369 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 5.9969. Min Range: -5.9969

Max Act: 5.6844. Min Act: -0.1700

Data Index: 370369 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 5.9969. Min Range: -5.9969

Max Act: 5.6844. Min Act: -0.1700

Data Index: 964873 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 5.9969. Min Range: -5.9969

Max Act: 5.6844. Min Act: -0.1700

Data Index: 778898 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 5.9969. Min Range: -5.9969

Max Act: 5.6532. Min Act: -0.1700

Data Index: 330856 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 5.9969. Min Range: -5.9969

Max Act: 5.6844. Min Act: -0.1700

Data Index: 1239511 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 5.9969. Min Range: -5.9969

Max Act: 5.6844. Min Act: -0.1700

Data Index: 161976 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 5.9969. Min Range: -5.9969

Max Act: 5.6844. Min Act: -0.1700

Data Index: 869235 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 5.9969. Min Range: -5.9969

Max Act: 5.6219. Min Act: -0.1700

Data Index: 1257945 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 5.9969. Min Range: -5.9969

Max Act: 5.6219. Min Act: -0.1700

Data Index: 233218 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 5.9969. Min Range: -5.9969

Max Act: 5.6219. Min Act: -0.1700

Data Index: 156250 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 5.9969. Min Range: -5.9969

Max Act: 5.6219. Min Act: -0.1700

Data Index: 710550 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 5.9969. Min Range: -5.9969

Max Act: 5.5282. Min Act: -0.1700

Data Index: 174926 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 5.9969. Min Range: -5.9969

Max Act: 5.5594. Min Act: -0.1700

Data Index: 1206485 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 5.9969. Min Range: -5.9969

Max Act: 5.5907. Min Act: -0.1700

Data Index: 149455 (C4 (Web Text))

Max Activating Token Index: 500