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

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

Neuron 1425 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: 3.3081. Min Range: -3.3081

Max Act: 3.3081. Min Act: -0.1700

Data Index: 447656 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 3.3081. Min Range: -3.3081

Max Act: 3.2610. Min Act: -0.1700

Data Index: 697352 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 3.3081. Min Range: -3.3081

Max Act: 3.2453. Min Act: -0.1700

Data Index: 577090 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 3.3081. Min Range: -3.3081

Max Act: 3.1981. Min Act: -0.1700

Data Index: 532009 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 3.3081. Min Range: -3.3081

Max Act: 3.1351. Min Act: -0.1700

Data Index: 976853 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 3.3081. Min Range: -3.3081

Max Act: 3.1193. Min Act: -0.1700

Data Index: 328393 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 3.3081. Min Range: -3.3081

Max Act: 3.1193. Min Act: -0.1700

Data Index: 810054 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 3.3081. Min Range: -3.3081

Max Act: 3.0878. Min Act: -0.1700

Data Index: 399591 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 3.3081. Min Range: -3.3081

Max Act: 3.0720. Min Act: -0.1700

Data Index: 38058 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 3.3081. Min Range: -3.3081

Max Act: 3.0878. Min Act: -0.1700

Data Index: 265173 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 3.3081. Min Range: -3.3081

Max Act: 3.0878. Min Act: -0.1700

Data Index: 747739 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 3.3081. Min Range: -3.3081

Max Act: 3.0878. Min Act: -0.1700

Data Index: 1294784 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 3.3081. Min Range: -3.3081

Max Act: 3.0720. Min Act: -0.1700

Data Index: 266375 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 3.3081. Min Range: -3.3081

Max Act: 3.0405. Min Act: -0.1700

Data Index: 609265 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 3.3081. Min Range: -3.3081

Max Act: 3.0563. Min Act: -0.1700

Data Index: 1072981 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 3.3081. Min Range: -3.3081

Max Act: 3.0563. Min Act: -0.1700

Data Index: 425578 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 3.3081. Min Range: -3.3081

Max Act: 3.0563. Min Act: -0.1700

Data Index: 8657 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 3.3081. Min Range: -3.3081

Max Act: 3.0089. Min Act: -0.1700

Data Index: 219246 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 3.3081. Min Range: -3.3081

Max Act: 3.0405. Min Act: -0.1700

Data Index: 862 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.3081. Min Range: -3.3081

Max Act: 3.0247. Min Act: -0.1700

Data Index: 1239720 (C4 (Web Text))

Max Activating Token Index: 638