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

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

Neuron 1811 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: 3.1051. Min Range: -3.1051

Max Act: 3.1051. Min Act: -0.1700

Data Index: 337669 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 3.1051. Min Range: -3.1051

Max Act: 3.0578. Min Act: -0.1700

Data Index: 270361 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 3.1051. Min Range: -3.1051

Max Act: 3.0578. Min Act: -0.1700

Data Index: 881761 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 3.1051. Min Range: -3.1051

Max Act: 3.0420. Min Act: -0.1700

Data Index: 781525 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 3.1051. Min Range: -3.1051

Max Act: 3.0420. Min Act: -0.1700

Data Index: 1349110 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 3.1051. Min Range: -3.1051

Max Act: 3.0262. Min Act: -0.1700

Data Index: 65084 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 3.1051. Min Range: -3.1051

Max Act: 3.0420. Min Act: -0.1700

Data Index: 1108571 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 3.1051. Min Range: -3.1051

Max Act: 3.0104. Min Act: -0.1700

Data Index: 826000 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 3.1051. Min Range: -3.1051

Max Act: 3.0104. Min Act: -0.1700

Data Index: 329518 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 3.1051. Min Range: -3.1051

Max Act: 3.0104. Min Act: -0.1700

Data Index: 619634 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 3.1051. Min Range: -3.1051

Max Act: 3.0262. Min Act: -0.1700

Data Index: 1219589 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 3.1051. Min Range: -3.1051

Max Act: 3.0104. Min Act: -0.1700

Data Index: 581019 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 3.1051. Min Range: -3.1051

Max Act: 3.0262. Min Act: -0.1700

Data Index: 1185974 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 3.1051. Min Range: -3.1051

Max Act: 3.0262. Min Act: -0.1700

Data Index: 648048 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.9946. Min Act: -0.1700

Data Index: 1191530 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 3.1051. Min Range: -3.1051

Max Act: 3.0262. Min Act: -0.1700

Data Index: 308034 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.9946. Min Act: -0.1700

Data Index: 612906 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 3.1051. Min Range: -3.1051

Max Act: 3.0104. Min Act: -0.1700

Data Index: 957538 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.9946. Min Act: -0.1700

Data Index: 656262 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 3.1051. Min Range: -3.1051

Max Act: 2.9788. Min Act: -0.1700

Data Index: 148099 (C4 (Web Text))

Max Activating Token Index: 862