Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1674 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.4154. Min Act: -0.1700

Data Index: 481203 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.4781. Min Act: -0.1700

Data Index: 1024116 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.4154. Min Act: -0.1700

Data Index: 659541 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.3683. Min Act: -0.1700

Data Index: 257723 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.3840. Min Act: -0.1700

Data Index: 598440 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.3526. Min Act: -0.1700

Data Index: 81884 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.3526. Min Act: -0.1700

Data Index: 657640 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.3683. Min Act: -0.1700

Data Index: 633934 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.3526. Min Act: -0.1700

Data Index: 1349754 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.3840. Min Act: -0.1700

Data Index: 1162575 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.3683. Min Act: -0.1700

Data Index: 1110442 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.3683. Min Act: -0.1700

Data Index: 639659 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.3840. Min Act: -0.1700

Data Index: 517720 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.4154. Min Act: -0.1700

Data Index: 527448 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.3212. Min Act: -0.1700

Data Index: 801394 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.3369. Min Act: -0.1700

Data Index: 929673 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.3526. Min Act: -0.1700

Data Index: 1104403 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.3212. Min Act: -0.1700

Data Index: 890748 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.3369. Min Act: -0.1700

Data Index: 650216 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 3.4781. Min Range: -3.4781

Max Act: 3.3526. Min Act: -0.1700

Data Index: 999751 (C4 (Web Text))

Max Activating Token Index: 248