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

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

Neuron 1731 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: 5.2920. Min Range: -5.2920

Max Act: 5.2920. Min Act: -0.1700

Data Index: 323468 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.9795. Min Act: -0.1700

Data Index: 811584 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.9482. Min Act: -0.1700

Data Index: 1065911 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.9482. Min Act: -0.1700

Data Index: 1042734 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.9170. Min Act: -0.1700

Data Index: 767668 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.9170. Min Act: -0.1700

Data Index: 550120 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.9170. Min Act: -0.1700

Data Index: 1358551 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.9170. Min Act: -0.1700

Data Index: 1023053 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.9170. Min Act: -0.1700

Data Index: 360570 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.8857. Min Act: -0.1700

Data Index: 463952 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.8545. Min Act: -0.1700

Data Index: 495134 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.8857. Min Act: -0.1700

Data Index: 164065 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.8232. Min Act: -0.1700

Data Index: 135481 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.8857. Min Act: -0.1700

Data Index: 152536 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.8545. Min Act: -0.1700

Data Index: 301713 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.8232. Min Act: -0.1700

Data Index: 785448 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.8232. Min Act: -0.1700

Data Index: 1027348 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.8545. Min Act: -0.1700

Data Index: 11032 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.8232. Min Act: -0.1700

Data Index: 256882 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.7920. Min Act: -0.1700

Data Index: 1307066 (C4 (Web Text))

Max Activating Token Index: 103