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

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

Neuron 530 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: 5.0452. Min Range: -5.0452

Max Act: 5.0452. Min Act: -0.1700

Data Index: 417441 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 5.0452. Min Range: -5.0452

Max Act: 5.0452. Min Act: -0.1700

Data Index: 1105670 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 5.0452. Min Range: -5.0452

Max Act: 5.0140. Min Act: -0.1700

Data Index: 990979 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 5.0452. Min Range: -5.0452

Max Act: 4.9515. Min Act: -0.1700

Data Index: 606406 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 5.0452. Min Range: -5.0452

Max Act: 4.8890. Min Act: -0.1700

Data Index: 773249 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 5.0452. Min Range: -5.0452

Max Act: 4.9202. Min Act: -0.1700

Data Index: 587305 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 5.0452. Min Range: -5.0452

Max Act: 4.8577. Min Act: -0.1700

Data Index: 677860 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 5.0452. Min Range: -5.0452

Max Act: 4.8577. Min Act: -0.1700

Data Index: 55601 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 5.0452. Min Range: -5.0452

Max Act: 4.8890. Min Act: -0.1700

Data Index: 1112253 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 5.0452. Min Range: -5.0452

Max Act: 4.8577. Min Act: -0.1700

Data Index: 596068 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 5.0452. Min Range: -5.0452

Max Act: 4.8265. Min Act: -0.1700

Data Index: 404488 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 5.0452. Min Range: -5.0452

Max Act: 4.8265. Min Act: -0.1700

Data Index: 183193 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 5.0452. Min Range: -5.0452

Max Act: 4.8265. Min Act: -0.1700

Data Index: 870285 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 5.0452. Min Range: -5.0452

Max Act: 4.7952. Min Act: -0.1700

Data Index: 541542 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 5.0452. Min Range: -5.0452

Max Act: 4.7640. Min Act: -0.1700

Data Index: 132388 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 5.0452. Min Range: -5.0452

Max Act: 4.7952. Min Act: -0.1700

Data Index: 1279669 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 5.0452. Min Range: -5.0452

Max Act: 4.7952. Min Act: -0.1700

Data Index: 1074333 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 5.0452. Min Range: -5.0452

Max Act: 4.7952. Min Act: -0.1700

Data Index: 754749 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 5.0452. Min Range: -5.0452

Max Act: 4.7640. Min Act: -0.1700

Data Index: 21434 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 5.0452. Min Range: -5.0452

Max Act: 4.7640. Min Act: -0.1700

Data Index: 865749 (C4 (Web Text))

Max Activating Token Index: 951