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

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

Neuron 28 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.1477. Min Act: -0.1700

Data Index: 398380 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.1477. Min Act: -0.1700

Data Index: 300077 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.1162. Min Act: -0.1700

Data Index: 580281 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.1162. Min Act: -0.1700

Data Index: 192745 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.1162. Min Act: -0.1700

Data Index: 617353 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0847. Min Act: -0.1700

Data Index: 38260 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0847. Min Act: -0.1700

Data Index: 158636 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0847. Min Act: -0.1700

Data Index: 1242516 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0689. Min Act: -0.1700

Data Index: 802454 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0531. Min Act: -0.1700

Data Index: 96955 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0689. Min Act: -0.1700

Data Index: 916611 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0531. Min Act: -0.1700

Data Index: 459537 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0531. Min Act: -0.1700

Data Index: 224168 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0215. Min Act: -0.1700

Data Index: 300686 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0215. Min Act: -0.1700

Data Index: 606453 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0215. Min Act: -0.1700

Data Index: 881224 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0057. Min Act: -0.1700

Data Index: 524099 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0057. Min Act: -0.1700

Data Index: 364580 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0215. Min Act: -0.1700

Data Index: 425105 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 3.1477. Min Range: -3.1477

Max Act: 2.9899. Min Act: -0.1700

Data Index: 997052 (C4 (Web Text))

Max Activating Token Index: 297