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

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

Neuron 1741 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2036. Min Range: -5.2036

Max Act: 5.1723. Min Act: -0.1700

Data Index: 30865 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 5.2036. Min Range: -5.2036

Max Act: 5.1411. Min Act: -0.1700

Data Index: 550394 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 5.2036. Min Range: -5.2036

Max Act: 5.2036. Min Act: -0.1700

Data Index: 504524 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 5.2036. Min Range: -5.2036

Max Act: 5.0786. Min Act: -0.1700

Data Index: 1090350 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 5.2036. Min Range: -5.2036

Max Act: 5.1098. Min Act: -0.1700

Data Index: 529930 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 5.2036. Min Range: -5.2036

Max Act: 5.1098. Min Act: -0.1700

Data Index: 477694 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 5.2036. Min Range: -5.2036

Max Act: 5.0161. Min Act: -0.1700

Data Index: 1319727 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 5.2036. Min Range: -5.2036

Max Act: 5.0786. Min Act: -0.1700

Data Index: 84401 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 5.2036. Min Range: -5.2036

Max Act: 4.9848. Min Act: -0.1700

Data Index: 610299 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 5.2036. Min Range: -5.2036

Max Act: 5.0161. Min Act: -0.1700

Data Index: 716201 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 5.2036. Min Range: -5.2036

Max Act: 5.0161. Min Act: -0.1700

Data Index: 544493 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 5.2036. Min Range: -5.2036

Max Act: 4.9848. Min Act: -0.1700

Data Index: 457222 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 5.2036. Min Range: -5.2036

Max Act: 4.9536. Min Act: -0.1700

Data Index: 350803 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 5.2036. Min Range: -5.2036

Max Act: 4.9848. Min Act: -0.1700

Data Index: 1015829 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 5.2036. Min Range: -5.2036

Max Act: 4.9536. Min Act: -0.1700

Data Index: 970107 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 5.2036. Min Range: -5.2036

Max Act: 4.9848. Min Act: -0.1700

Data Index: 249765 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 5.2036. Min Range: -5.2036

Max Act: 4.9536. Min Act: -0.1700

Data Index: 1241760 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 5.2036. Min Range: -5.2036

Max Act: 5.0161. Min Act: -0.1700

Data Index: 1278705 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 5.2036. Min Range: -5.2036

Max Act: 4.9223. Min Act: -0.1700

Data Index: 779378 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 5.2036. Min Range: -5.2036

Max Act: 4.8911. Min Act: -0.1700

Data Index: 719600 (C4 (Web Text))

Max Activating Token Index: 870