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

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

Neuron 535 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.6379. Min Act: -0.1700

Data Index: 1175804 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.5413. Min Act: -0.1700

Data Index: 1245843 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.4766. Min Act: -0.1700

Data Index: 781098 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.4441. Min Act: -0.1700

Data Index: 619057 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.4278. Min Act: -0.1700

Data Index: 950989 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.4115. Min Act: -0.1700

Data Index: 4594 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.4278. Min Act: -0.1700

Data Index: 1028808 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.4115. Min Act: -0.1700

Data Index: 478787 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.4278. Min Act: -0.1700

Data Index: 171029 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.3952. Min Act: -0.1700

Data Index: 294672 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.3952. Min Act: -0.1700

Data Index: 967981 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.3952. Min Act: -0.1700

Data Index: 978858 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.4115. Min Act: -0.1700

Data Index: 1175358 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.4115. Min Act: -0.1700

Data Index: 708354 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.4115. Min Act: -0.1700

Data Index: 21102 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.4115. Min Act: -0.1700

Data Index: 783264 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.3952. Min Act: -0.1700

Data Index: 800479 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.3952. Min Act: -0.1700

Data Index: 383943 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.3952. Min Act: -0.1700

Data Index: 612554 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 2.6379. Min Range: -2.6379

Max Act: 2.3952. Min Act: -0.1700

Data Index: 842941 (C4 (Web Text))

Max Activating Token Index: 727