Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1728 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.1325. Min Act: -0.1700

Data Index: 102396 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.1010. Min Act: -0.1700

Data Index: 737001 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.1010. Min Act: -0.1700

Data Index: 239622 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0536. Min Act: -0.1700

Data Index: 656056 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9904. Min Act: -0.1700

Data Index: 1000061 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0221. Min Act: -0.1700

Data Index: 951803 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0221. Min Act: -0.1700

Data Index: 420740 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0062. Min Act: -0.1700

Data Index: 1336806 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0221. Min Act: -0.1700

Data Index: 857255 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0062. Min Act: -0.1700

Data Index: 1336401 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0062. Min Act: -0.1700

Data Index: 387408 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0062. Min Act: -0.1700

Data Index: 1043320 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0062. Min Act: -0.1700

Data Index: 792464 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0062. Min Act: -0.1700

Data Index: 1180272 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0062. Min Act: -0.1700

Data Index: 1024480 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9904. Min Act: -0.1700

Data Index: 932835 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9904. Min Act: -0.1700

Data Index: 1235636 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9904. Min Act: -0.1700

Data Index: 715481 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9746. Min Act: -0.1700

Data Index: 1004050 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0062. Min Act: -0.1700

Data Index: 57590 (C4 (Web Text))

Max Activating Token Index: 14