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

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

Neuron 1843 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: 7.2938. Min Range: -7.2938

Max Act: 7.2938. Min Act: -0.1700

Data Index: 713981 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 7.2938. Min Range: -7.2938

Max Act: 7.2313. Min Act: -0.1700

Data Index: 619280 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 7.2938. Min Range: -7.2938

Max Act: 7.2313. Min Act: -0.1700

Data Index: 1591842 (Python Code)

Max Activating Token Index: 481

Text #3

Max Range: 7.2938. Min Range: -7.2938

Max Act: 7.1063. Min Act: -0.1700

Data Index: 474521 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 7.2938. Min Range: -7.2938

Max Act: 6.8563. Min Act: -0.1700

Data Index: 50394 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 7.2938. Min Range: -7.2938

Max Act: 6.9501. Min Act: -0.1700

Data Index: 170069 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 7.2938. Min Range: -7.2938

Max Act: 6.8876. Min Act: -0.1700

Data Index: 1154553 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 7.2938. Min Range: -7.2938

Max Act: 6.7001. Min Act: -0.1700

Data Index: 974824 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 7.2938. Min Range: -7.2938

Max Act: 6.8251. Min Act: -0.1700

Data Index: 1283554 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 7.2938. Min Range: -7.2938

Max Act: 6.8251. Min Act: -0.1700

Data Index: 1096147 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 7.2938. Min Range: -7.2938

Max Act: 6.7313. Min Act: -0.1700

Data Index: 318652 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 7.2938. Min Range: -7.2938

Max Act: 6.7313. Min Act: -0.1700

Data Index: 210832 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 7.2938. Min Range: -7.2938

Max Act: 6.6688. Min Act: -0.1700

Data Index: 386380 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 7.2938. Min Range: -7.2938

Max Act: 6.9188. Min Act: -0.1700

Data Index: 970889 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 7.2938. Min Range: -7.2938

Max Act: 6.8251. Min Act: -0.1700

Data Index: 786906 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 7.2938. Min Range: -7.2938

Max Act: 6.7626. Min Act: -0.1700

Data Index: 661733 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 7.2938. Min Range: -7.2938

Max Act: 6.7001. Min Act: -0.1700

Data Index: 57415 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 7.2938. Min Range: -7.2938

Max Act: 6.6688. Min Act: -0.1700

Data Index: 202292 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 7.2938. Min Range: -7.2938

Max Act: 6.7313. Min Act: -0.1700

Data Index: 930924 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 7.2938. Min Range: -7.2938

Max Act: 6.7001. Min Act: -0.1700

Data Index: 348526 (C4 (Web Text))

Max Activating Token Index: 647