Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1677 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.6727. Min Act: -0.1700

Data Index: 509380 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.6414. Min Act: -0.1700

Data Index: 1216467 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.6257. Min Act: -0.1700

Data Index: 840081 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5631. Min Act: -0.1700

Data Index: 1420535 (Python Code)

Max Activating Token Index: 301

Text #4

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5944. Min Act: -0.1700

Data Index: 1607124 (Python Code)

Max Activating Token Index: 486

Text #5

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5787. Min Act: -0.1700

Data Index: 1436377 (Python Code)

Max Activating Token Index: 517

Text #6

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5631. Min Act: -0.1700

Data Index: 1532882 (Python Code)

Max Activating Token Index: 680

Text #7

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5474. Min Act: -0.1700

Data Index: 1420001 (Python Code)

Max Activating Token Index: 235

Text #8

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5317. Min Act: -0.1700

Data Index: 341754 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5317. Min Act: -0.1700

Data Index: 1590324 (Python Code)

Max Activating Token Index: 793

Text #10

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5631. Min Act: -0.1700

Data Index: 1457161 (Python Code)

Max Activating Token Index: 474

Text #11

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5161. Min Act: -0.1700

Data Index: 1592744 (Python Code)

Max Activating Token Index: 794

Text #12

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5317. Min Act: -0.1700

Data Index: 1152472 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5161. Min Act: -0.1700

Data Index: 1316736 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5474. Min Act: -0.1700

Data Index: 1589083 (Python Code)

Max Activating Token Index: 331

Text #15

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5161. Min Act: -0.1700

Data Index: 1603611 (Python Code)

Max Activating Token Index: 191

Text #16

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5317. Min Act: -0.1700

Data Index: 1590618 (Python Code)

Max Activating Token Index: 154

Text #17

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5161. Min Act: -0.1700

Data Index: 1210398 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5317. Min Act: -0.1700

Data Index: 1404552 (Python Code)

Max Activating Token Index: 565

Text #19

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5161. Min Act: -0.1700

Data Index: 1653568 (Python Code)

Max Activating Token Index: 429