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

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

Neuron 513 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: 5.0524. Min Range: -5.0524

Max Act: 5.0524. Min Act: -0.1700

Data Index: 790332 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 5.0524. Min Range: -5.0524

Max Act: 4.9742. Min Act: -0.1700

Data Index: 1124992 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 5.0524. Min Range: -5.0524

Max Act: 4.8649. Min Act: -0.1700

Data Index: 104086 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 5.0524. Min Range: -5.0524

Max Act: 4.8024. Min Act: -0.1700

Data Index: 1100508 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 5.0524. Min Range: -5.0524

Max Act: 4.8492. Min Act: -0.1700

Data Index: 927364 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 5.0524. Min Range: -5.0524

Max Act: 4.8180. Min Act: -0.1700

Data Index: 1064095 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 5.0524. Min Range: -5.0524

Max Act: 4.7555. Min Act: -0.1700

Data Index: 268513 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 5.0524. Min Range: -5.0524

Max Act: 4.7867. Min Act: -0.1700

Data Index: 221928 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 5.0524. Min Range: -5.0524

Max Act: 4.7555. Min Act: -0.1700

Data Index: 79033 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 5.0524. Min Range: -5.0524

Max Act: 4.7711. Min Act: -0.1700

Data Index: 964496 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 5.0524. Min Range: -5.0524

Max Act: 4.7399. Min Act: -0.1700

Data Index: 336459 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 5.0524. Min Range: -5.0524

Max Act: 4.7399. Min Act: -0.1700

Data Index: 341515 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 5.0524. Min Range: -5.0524

Max Act: 4.7399. Min Act: -0.1700

Data Index: 345097 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 5.0524. Min Range: -5.0524

Max Act: 4.7086. Min Act: -0.1700

Data Index: 299869 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 5.0524. Min Range: -5.0524

Max Act: 4.7711. Min Act: -0.1700

Data Index: 1144901 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 5.0524. Min Range: -5.0524

Max Act: 4.7086. Min Act: -0.1700

Data Index: 719208 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 5.0524. Min Range: -5.0524

Max Act: 4.7086. Min Act: -0.1700

Data Index: 930905 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 5.0524. Min Range: -5.0524

Max Act: 4.6461. Min Act: -0.1700

Data Index: 440550 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 5.0524. Min Range: -5.0524

Max Act: 4.6305. Min Act: -0.1700

Data Index: 1100140 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 5.0524. Min Range: -5.0524

Max Act: 4.6930. Min Act: -0.1700

Data Index: 555893 (C4 (Web Text))

Max Activating Token Index: 157