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

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

Neuron 1551 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: 3.9731. Min Range: -3.9731

Max Act: 3.9731. Min Act: -0.1700

Data Index: 1346472 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9419. Min Act: -0.1700

Data Index: 867698 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9419. Min Act: -0.1700

Data Index: 718744 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9106. Min Act: -0.1700

Data Index: 708639 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9106. Min Act: -0.1700

Data Index: 179606 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9106. Min Act: -0.1700

Data Index: 656384 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8793. Min Act: -0.1700

Data Index: 438071 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8793. Min Act: -0.1700

Data Index: 380787 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8168. Min Act: -0.1700

Data Index: 201273 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8168. Min Act: -0.1700

Data Index: 765170 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8480. Min Act: -0.1700

Data Index: 1174159 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8480. Min Act: -0.1700

Data Index: 264825 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8793. Min Act: -0.1700

Data Index: 1258452 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.7855. Min Act: -0.1700

Data Index: 1300112 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8168. Min Act: -0.1700

Data Index: 410852 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8168. Min Act: -0.1700

Data Index: 1035205 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8168. Min Act: -0.1700

Data Index: 991841 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8168. Min Act: -0.1700

Data Index: 896481 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.7855. Min Act: -0.1700

Data Index: 339426 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.7855. Min Act: -0.1700

Data Index: 360094 (C4 (Web Text))

Max Activating Token Index: 17