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

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

Neuron 291 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.6347. Min Act: -0.1700

Data Index: 1574780 (Python Code)

Max Activating Token Index: 784

Text #1

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.6191. Min Act: -0.1700

Data Index: 506053 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.5722. Min Act: -0.1700

Data Index: 1630222 (Python Code)

Max Activating Token Index: 327

Text #3

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.4941. Min Act: -0.1700

Data Index: 1480739 (Python Code)

Max Activating Token Index: 409

Text #4

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.4160. Min Act: -0.1700

Data Index: 391227 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.3535. Min Act: -0.1700

Data Index: 819434 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.2441. Min Act: -0.1700

Data Index: 376544 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.2441. Min Act: -0.1700

Data Index: 342219 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.2129. Min Act: -0.1700

Data Index: 83721 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.2441. Min Act: -0.1700

Data Index: 1542581 (Python Code)

Max Activating Token Index: 931

Text #10

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.1347. Min Act: -0.1700

Data Index: 1513307 (Python Code)

Max Activating Token Index: 446

Text #11

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.1191. Min Act: -0.1700

Data Index: 1367286 (Python Code)

Max Activating Token Index: 43

Text #12

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.1816. Min Act: -0.1700

Data Index: 593874 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.1660. Min Act: -0.1700

Data Index: 450465 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.1660. Min Act: -0.1700

Data Index: 878058 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.1191. Min Act: -0.1700

Data Index: 1603903 (Python Code)

Max Activating Token Index: 53

Text #16

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.1035. Min Act: -0.1700

Data Index: 1640783 (Python Code)

Max Activating Token Index: 814

Text #17

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.1347. Min Act: -0.1699

Data Index: 542454 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.1347. Min Act: -0.1700

Data Index: 1633618 (Python Code)

Max Activating Token Index: 102

Text #19

Max Range: 5.6347. Min Range: -5.6347

Max Act: 5.0722. Min Act: -0.1700

Data Index: 1386510 (Python Code)

Max Activating Token Index: 612