Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 569 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.5089. Min Act: -0.1700

Data Index: 163272 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.3839. Min Act: -0.1700

Data Index: 124843 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.4464. Min Act: -0.1700

Data Index: 659215 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.4777. Min Act: -0.1700

Data Index: 122712 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.4464. Min Act: -0.1700

Data Index: 727782 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.3214. Min Act: -0.1700

Data Index: 292494 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.2589. Min Act: -0.1700

Data Index: 48254 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.1964. Min Act: -0.1700

Data Index: 857513 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.2589. Min Act: -0.1700

Data Index: 638771 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.2277. Min Act: -0.1700

Data Index: 1024688 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.2277. Min Act: -0.1700

Data Index: 330756 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.1027. Min Act: -0.1700

Data Index: 1202879 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.1964. Min Act: -0.1700

Data Index: 1067000 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.1652. Min Act: -0.1700

Data Index: 217798 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.0402. Min Act: -0.1700

Data Index: 518316 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.0714. Min Act: -0.1700

Data Index: 517691 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.0402. Min Act: -0.1700

Data Index: 498613 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.0714. Min Act: -0.1700

Data Index: 371834 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.0402. Min Act: -0.1700

Data Index: 1290631 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 5.5089. Min Range: -5.5089

Max Act: 5.1027. Min Act: -0.1700

Data Index: 636695 (C4 (Web Text))

Max Activating Token Index: 49