Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1817 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.4752. Min Act: -0.1700

Data Index: 460132 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.3381. Min Act: -0.1700

Data Index: 274579 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.2834. Min Act: -0.1700

Data Index: 645463 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.2813. Min Act: -0.1700

Data Index: 379311 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.2495. Min Act: -0.1700

Data Index: 218098 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.2544. Min Act: -0.1700

Data Index: 821778 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.2602. Min Act: -0.1700

Data Index: 293374 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.2421. Min Act: -0.1700

Data Index: 691348 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.2239. Min Act: -0.1700

Data Index: 1233063 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.2206. Min Act: -0.1700

Data Index: 819356 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.2192. Min Act: -0.1700

Data Index: 76005 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.2106. Min Act: -0.1700

Data Index: 341230 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.1975. Min Act: -0.1700

Data Index: 712220 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.2186. Min Act: -0.1700

Data Index: 455631 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.2305. Min Act: -0.1700

Data Index: 155576 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.2394. Min Act: -0.1700

Data Index: 1142523 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.1878. Min Act: -0.1700

Data Index: 1056153 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.1994. Min Act: -0.1700

Data Index: 618488 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.1991. Min Act: -0.1700

Data Index: 988320 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 4.4752. Min Range: -4.4752

Max Act: 4.1606. Min Act: -0.1700

Data Index: 133296 (C4 (Web Text))

Max Activating Token Index: 52