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

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

Neuron 640 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: 3.0753. Min Range: -3.0753

Max Act: 3.0753. Min Act: -0.1700

Data Index: 1603660 (Python Code)

Max Activating Token Index: 844

Text #1

Max Range: 3.0753. Min Range: -3.0753

Max Act: 3.0274. Min Act: -0.1700

Data Index: 1081179 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 3.0753. Min Range: -3.0753

Max Act: 3.0001. Min Act: -0.1700

Data Index: 611933 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 3.0753. Min Range: -3.0753

Max Act: 3.0066. Min Act: -0.1700

Data Index: 604598 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 3.0753. Min Range: -3.0753

Max Act: 3.0060. Min Act: -0.1700

Data Index: 1135715 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.9723. Min Act: -0.1700

Data Index: 197527 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.9573. Min Act: -0.1700

Data Index: 587375 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.9509. Min Act: -0.1700

Data Index: 1159822 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.9356. Min Act: -0.1700

Data Index: 1168645 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.9296. Min Act: -0.1700

Data Index: 804718 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.9163. Min Act: -0.1700

Data Index: 772333 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.9136. Min Act: -0.1700

Data Index: 773372 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.9197. Min Act: -0.1700

Data Index: 232237 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.9185. Min Act: -0.1341

Data Index: 243080 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.9148. Min Act: -0.1700

Data Index: 1045619 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.8989. Min Act: -0.1700

Data Index: 1073067 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.9093. Min Act: -0.1700

Data Index: 139692 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.9051. Min Act: -0.1690

Data Index: 738107 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.9042. Min Act: -0.1700

Data Index: 1108048 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.9107. Min Act: -0.1700

Data Index: 1143512 (C4 (Web Text))

Max Activating Token Index: 729