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

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

Neuron 4 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: 3.3392. Min Range: -3.3392

Max Act: 3.3392. Min Act: -0.1700

Data Index: 164995 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.3078. Min Act: -0.1700

Data Index: 356044 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.3078. Min Act: -0.1700

Data Index: 1320813 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.2764. Min Act: -0.1700

Data Index: 106981 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.2764. Min Act: -0.1700

Data Index: 323712 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.2764. Min Act: -0.1700

Data Index: 268911 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.2450. Min Act: -0.1700

Data Index: 388577 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.2135. Min Act: -0.1700

Data Index: 317825 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.2293. Min Act: -0.1700

Data Index: 628623 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.2450. Min Act: -0.1700

Data Index: 623214 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.2135. Min Act: -0.1700

Data Index: 326895 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.1978. Min Act: -0.1700

Data Index: 708410 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.2293. Min Act: -0.1700

Data Index: 1352951 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.1978. Min Act: -0.1700

Data Index: 665011 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.1663. Min Act: -0.1700

Data Index: 715597 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.1506. Min Act: -0.1700

Data Index: 248713 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.1821. Min Act: -0.1700

Data Index: 1103383 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.1663. Min Act: -0.1700

Data Index: 352948 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.1663. Min Act: -0.1700

Data Index: 309697 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.1506. Min Act: -0.1700

Data Index: 866623 (C4 (Web Text))

Max Activating Token Index: 256