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

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

Neuron 1222 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.6368. Min Act: -0.1700

Data Index: 981368 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.6368. Min Act: -0.1700

Data Index: 521557 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.6212. Min Act: -0.1700

Data Index: 1293933 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.5899. Min Act: -0.1700

Data Index: 1086498 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.5899. Min Act: -0.1700

Data Index: 1037164 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.5586. Min Act: -0.1700

Data Index: 750444 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.5586. Min Act: -0.1700

Data Index: 1015300 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.5742. Min Act: -0.1700

Data Index: 177729 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.5586. Min Act: -0.1700

Data Index: 1443343 (Python Code)

Max Activating Token Index: 631

Text #9

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.5586. Min Act: -0.1700

Data Index: 1153796 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.5586. Min Act: -0.1700

Data Index: 56586 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.5429. Min Act: -0.1700

Data Index: 1202031 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.5272. Min Act: -0.1700

Data Index: 103988 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.5429. Min Act: -0.1700

Data Index: 1339224 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.5429. Min Act: -0.1700

Data Index: 573605 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.5429. Min Act: -0.1700

Data Index: 698978 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.5429. Min Act: -0.1700

Data Index: 48535 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.5429. Min Act: -0.1700

Data Index: 757588 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.5116. Min Act: -0.1700

Data Index: 489497 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 3.6368. Min Range: -3.6368

Max Act: 3.5429. Min Act: -0.1700

Data Index: 1022453 (C4 (Web Text))

Max Activating Token Index: 669