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

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

Neuron 416 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: 3.7626. Min Range: -3.7626

Max Act: 3.7626. Min Act: -0.1697

Data Index: 306920 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 3.7626. Min Range: -3.7626

Max Act: 3.7247. Min Act: -0.1700

Data Index: 429519 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 3.7626. Min Range: -3.7626

Max Act: 3.6646. Min Act: -0.1698

Data Index: 61871 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 3.7626. Min Range: -3.7626

Max Act: 3.6312. Min Act: -0.1696

Data Index: 310975 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 3.7626. Min Range: -3.7626

Max Act: 3.5713. Min Act: -0.1700

Data Index: 640295 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 3.7626. Min Range: -3.7626

Max Act: 3.5512. Min Act: -0.1700

Data Index: 482492 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 3.7626. Min Range: -3.7626

Max Act: 3.5578. Min Act: -0.1695

Data Index: 66358 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 3.7626. Min Range: -3.7626

Max Act: 3.5257. Min Act: -0.1700

Data Index: 224123 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 3.7626. Min Range: -3.7626

Max Act: 3.4915. Min Act: -0.1698

Data Index: 302549 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 3.7626. Min Range: -3.7626

Max Act: 3.5038. Min Act: -0.1700

Data Index: 385492 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 3.7626. Min Range: -3.7626

Max Act: 3.5059. Min Act: -0.1700

Data Index: 1233943 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 3.7626. Min Range: -3.7626

Max Act: 3.4953. Min Act: -0.1700

Data Index: 967734 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 3.7626. Min Range: -3.7626

Max Act: 3.4936. Min Act: -0.1700

Data Index: 343898 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 3.7626. Min Range: -3.7626

Max Act: 3.4736. Min Act: -0.1700

Data Index: 1208452 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 3.7626. Min Range: -3.7626

Max Act: 3.4716. Min Act: -0.1700

Data Index: 1196098 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 3.7626. Min Range: -3.7626

Max Act: 3.4689. Min Act: -0.1700

Data Index: 376921 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 3.7626. Min Range: -3.7626

Max Act: 3.4553. Min Act: -0.1700

Data Index: 1225945 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 3.7626. Min Range: -3.7626

Max Act: 3.4545. Min Act: -0.1700

Data Index: 1231815 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 3.7626. Min Range: -3.7626

Max Act: 3.4470. Min Act: -0.1700

Data Index: 823700 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 3.7626. Min Range: -3.7626

Max Act: 3.4467. Min Act: -0.1700

Data Index: 828730 (C4 (Web Text))

Max Activating Token Index: 422