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

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

Neuron 1638 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: 2.8295. Min Range: -2.8295

Max Act: 2.8295. Min Act: -0.1700

Data Index: 783858 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 2.8295. Min Range: -2.8295

Max Act: 2.7848. Min Act: -0.1700

Data Index: 1317710 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 2.8295. Min Range: -2.8295

Max Act: 2.7781. Min Act: -0.1700

Data Index: 59569 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 2.8295. Min Range: -2.8295

Max Act: 2.7251. Min Act: -0.1700

Data Index: 1081352 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 2.8295. Min Range: -2.8295

Max Act: 2.7196. Min Act: -0.1700

Data Index: 1193681 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 2.8295. Min Range: -2.8295

Max Act: 2.7030. Min Act: -0.1700

Data Index: 720403 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 2.8295. Min Range: -2.8295

Max Act: 2.7075. Min Act: -0.1700

Data Index: 6257 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 2.8295. Min Range: -2.8295

Max Act: 2.7250. Min Act: -0.1700

Data Index: 465442 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 2.8295. Min Range: -2.8295

Max Act: 2.6935. Min Act: -0.1700

Data Index: 774863 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 2.8295. Min Range: -2.8295

Max Act: 2.7006. Min Act: -0.1700

Data Index: 217135 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 2.8295. Min Range: -2.8295

Max Act: 2.6904. Min Act: -0.1700

Data Index: 599807 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 2.8295. Min Range: -2.8295

Max Act: 2.6705. Min Act: -0.1700

Data Index: 1565117 (Python Code)

Max Activating Token Index: 368

Text #12

Max Range: 2.8295. Min Range: -2.8295

Max Act: 2.6799. Min Act: -0.1700

Data Index: 497215 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 2.8295. Min Range: -2.8295

Max Act: 2.6851. Min Act: -0.1700

Data Index: 741286 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 2.8295. Min Range: -2.8295

Max Act: 2.6723. Min Act: -0.1700

Data Index: 602970 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 2.8295. Min Range: -2.8295

Max Act: 2.6843. Min Act: -0.1700

Data Index: 244131 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 2.8295. Min Range: -2.8295

Max Act: 2.6788. Min Act: -0.1700

Data Index: 771756 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 2.8295. Min Range: -2.8295

Max Act: 2.6898. Min Act: -0.1700

Data Index: 374997 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 2.8295. Min Range: -2.8295

Max Act: 2.6781. Min Act: -0.1700

Data Index: 247906 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 2.8295. Min Range: -2.8295

Max Act: 2.6816. Min Act: -0.1700

Data Index: 704144 (C4 (Web Text))

Max Activating Token Index: 354