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

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

Neuron 1861 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3055. Min Range: -5.3055

Max Act: 5.3055. Min Act: -0.1700

Data Index: 1647974 (Python Code)

Max Activating Token Index: 924

Text #1

Max Range: 5.3055. Min Range: -5.3055

Max Act: 5.1180. Min Act: -0.1700

Data Index: 1403399 (Python Code)

Max Activating Token Index: 478

Text #2

Max Range: 5.3055. Min Range: -5.3055

Max Act: 5.1805. Min Act: -0.1700

Data Index: 1366151 (Python Code)

Max Activating Token Index: 628

Text #3

Max Range: 5.3055. Min Range: -5.3055

Max Act: 5.1180. Min Act: -0.1700

Data Index: 1468547 (Python Code)

Max Activating Token Index: 548

Text #4

Max Range: 5.3055. Min Range: -5.3055

Max Act: 5.1492. Min Act: -0.1700

Data Index: 1653100 (Python Code)

Max Activating Token Index: 569

Text #5

Max Range: 5.3055. Min Range: -5.3055

Max Act: 5.0867. Min Act: -0.1700

Data Index: 1497918 (Python Code)

Max Activating Token Index: 919

Text #6

Max Range: 5.3055. Min Range: -5.3055

Max Act: 5.0555. Min Act: -0.1700

Data Index: 1418841 (Python Code)

Max Activating Token Index: 518

Text #7

Max Range: 5.3055. Min Range: -5.3055

Max Act: 5.0555. Min Act: -0.1700

Data Index: 1601153 (Python Code)

Max Activating Token Index: 545

Text #8

Max Range: 5.3055. Min Range: -5.3055

Max Act: 4.9930. Min Act: -0.1700

Data Index: 171427 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 5.3055. Min Range: -5.3055

Max Act: 4.9930. Min Act: -0.1700

Data Index: 1505613 (Python Code)

Max Activating Token Index: 393

Text #10

Max Range: 5.3055. Min Range: -5.3055

Max Act: 5.0555. Min Act: -0.1700

Data Index: 813842 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 5.3055. Min Range: -5.3055

Max Act: 4.9617. Min Act: -0.1700

Data Index: 1516984 (Python Code)

Max Activating Token Index: 497

Text #12

Max Range: 5.3055. Min Range: -5.3055

Max Act: 4.9930. Min Act: -0.1700

Data Index: 1562765 (Python Code)

Max Activating Token Index: 644

Text #13

Max Range: 5.3055. Min Range: -5.3055

Max Act: 4.9930. Min Act: -0.1700

Data Index: 1562654 (Python Code)

Max Activating Token Index: 264

Text #14

Max Range: 5.3055. Min Range: -5.3055

Max Act: 4.9617. Min Act: -0.1700

Data Index: 437302 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 5.3055. Min Range: -5.3055

Max Act: 4.9617. Min Act: -0.1700

Data Index: 439915 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 5.3055. Min Range: -5.3055

Max Act: 4.9617. Min Act: -0.1700

Data Index: 1510552 (Python Code)

Max Activating Token Index: 365

Text #17

Max Range: 5.3055. Min Range: -5.3055

Max Act: 4.9305. Min Act: -0.1700

Data Index: 1444991 (Python Code)

Max Activating Token Index: 674

Text #18

Max Range: 5.3055. Min Range: -5.3055

Max Act: 4.9617. Min Act: -0.1700

Data Index: 1367618 (Python Code)

Max Activating Token Index: 503

Text #19

Max Range: 5.3055. Min Range: -5.3055

Max Act: 4.9305. Min Act: -0.1700

Data Index: 1409534 (Python Code)

Max Activating Token Index: 373