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

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

Neuron 642 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.5874. Min Act: -0.1700

Data Index: 17523 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.5249. Min Act: -0.1700

Data Index: 396849 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.4624. Min Act: -0.1700

Data Index: 819806 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.3999. Min Act: -0.1700

Data Index: 1154849 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.3999. Min Act: -0.1700

Data Index: 375809 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.3999. Min Act: -0.1700

Data Index: 563905 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.3374. Min Act: -0.1700

Data Index: 226443 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.2749. Min Act: -0.1700

Data Index: 468703 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.2124. Min Act: -0.1700

Data Index: 1634036 (Python Code)

Max Activating Token Index: 580

Text #9

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.2124. Min Act: -0.1700

Data Index: 1584155 (Python Code)

Max Activating Token Index: 720

Text #10

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.1499. Min Act: -0.1700

Data Index: 1378464 (Python Code)

Max Activating Token Index: 247

Text #11

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.2124. Min Act: -0.1700

Data Index: 827383 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.2124. Min Act: -0.1700

Data Index: 758995 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.2749. Min Act: -0.1700

Data Index: 588416 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.2124. Min Act: -0.1700

Data Index: 386457 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.1499. Min Act: -0.1700

Data Index: 655156 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.1499. Min Act: -0.1700

Data Index: 1004290 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.1499. Min Act: -0.1700

Data Index: 53561 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.2124. Min Act: -0.1700

Data Index: 601053 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 7.5874. Min Range: -7.5874

Max Act: 7.1499. Min Act: -0.1700

Data Index: 294544 (C4 (Web Text))

Max Activating Token Index: 999