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

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

Neuron 1424 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: 3.6010. Min Range: -3.6010

Max Act: 3.6010. Min Act: -0.1700

Data Index: 1368279 (Python Code)

Max Activating Token Index: 908

Text #1

Max Range: 3.6010. Min Range: -3.6010

Max Act: 3.5697. Min Act: -0.1700

Data Index: 1603659 (Python Code)

Max Activating Token Index: 201

Text #2

Max Range: 3.6010. Min Range: -3.6010

Max Act: 3.5541. Min Act: -0.1700

Data Index: 1498660 (Python Code)

Max Activating Token Index: 741

Text #3

Max Range: 3.6010. Min Range: -3.6010

Max Act: 3.5071. Min Act: -0.1700

Data Index: 1627502 (Python Code)

Max Activating Token Index: 916

Text #4

Max Range: 3.6010. Min Range: -3.6010

Max Act: 3.4757. Min Act: -0.1700

Data Index: 1585297 (Python Code)

Max Activating Token Index: 493

Text #5

Max Range: 3.6010. Min Range: -3.6010

Max Act: 3.4444. Min Act: -0.1700

Data Index: 1622163 (Python Code)

Max Activating Token Index: 466

Text #6

Max Range: 3.6010. Min Range: -3.6010

Max Act: 3.4444. Min Act: -0.1700

Data Index: 1502546 (Python Code)

Max Activating Token Index: 447

Text #7

Max Range: 3.6010. Min Range: -3.6010

Max Act: 3.4600. Min Act: -0.1700

Data Index: 1614721 (Python Code)

Max Activating Token Index: 707

Text #8

Max Range: 3.6010. Min Range: -3.6010

Max Act: 3.4287. Min Act: -0.1700

Data Index: 1467912 (Python Code)

Max Activating Token Index: 199

Text #9

Max Range: 3.6010. Min Range: -3.6010

Max Act: 3.3973. Min Act: -0.1700

Data Index: 1451488 (Python Code)

Max Activating Token Index: 675

Text #10

Max Range: 3.6010. Min Range: -3.6010

Max Act: 3.4130. Min Act: -0.1700

Data Index: 1458656 (Python Code)

Max Activating Token Index: 568

Text #11

Max Range: 3.6010. Min Range: -3.6010

Max Act: 3.4130. Min Act: -0.1700

Data Index: 1630283 (Python Code)

Max Activating Token Index: 609

Text #12

Max Range: 3.6010. Min Range: -3.6010

Max Act: 3.3973. Min Act: -0.1700

Data Index: 1609036 (Python Code)

Max Activating Token Index: 572

Text #13

Max Range: 3.6010. Min Range: -3.6010

Max Act: 3.2403. Min Act: -0.1700

Data Index: 1415174 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 3.6010. Min Range: -3.6010

Max Act: 3.2246. Min Act: -0.1700

Data Index: 1411241 (Python Code)

Max Activating Token Index: 734

Text #15

Max Range: 3.6010. Min Range: -3.6010

Max Act: 3.1931. Min Act: -0.1700

Data Index: 1022999 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 3.6010. Min Range: -3.6010

Max Act: 3.1616. Min Act: -0.1700

Data Index: 258731 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 3.6010. Min Range: -3.6010

Max Act: 3.1459. Min Act: -0.1700

Data Index: 1342296 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 3.6010. Min Range: -3.6010

Max Act: 3.1616. Min Act: -0.1700

Data Index: 107337 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 3.6010. Min Range: -3.6010

Max Act: 3.1301. Min Act: -0.1700

Data Index: 81638 (C4 (Web Text))

Max Activating Token Index: 834