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

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

Neuron 324 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: 3.2834. Min Range: -3.2834

Max Act: 3.2834. Min Act: -0.1699

Data Index: 1261848 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.2362. Min Act: -0.1700

Data Index: 119396 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.2519. Min Act: -0.1700

Data Index: 404837 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1890. Min Act: -0.1699

Data Index: 954822 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1890. Min Act: -0.1700

Data Index: 216092 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1576. Min Act: -0.1699

Data Index: 742622 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1576. Min Act: -0.1700

Data Index: 631132 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1418. Min Act: -0.1700

Data Index: 524242 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1418. Min Act: -0.1700

Data Index: 1047531 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1418. Min Act: -0.1700

Data Index: 417240 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1418. Min Act: -0.1700

Data Index: 845581 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1261. Min Act: -0.1700

Data Index: 1376100 (Python Code)

Max Activating Token Index: 617

Text #12

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1261. Min Act: -0.1700

Data Index: 761867 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1261. Min Act: -0.1700

Data Index: 251447 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1418. Min Act: -0.1700

Data Index: 574837 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1261. Min Act: -0.1700

Data Index: 708151 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1103. Min Act: -0.1700

Data Index: 299748 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1103. Min Act: -0.1700

Data Index: 14579 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1103. Min Act: -0.1700

Data Index: 416690 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 3.2834. Min Range: -3.2834

Max Act: 3.1103. Min Act: -0.1700

Data Index: 151714 (C4 (Web Text))

Max Activating Token Index: 1016