Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 225 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.6985. Min Act: -0.1700

Data Index: 1202003 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.2610. Min Act: -0.1700

Data Index: 1656379 (Python Code)

Max Activating Token Index: 575

Text #2

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.1985. Min Act: -0.1700

Data Index: 1449003 (Python Code)

Max Activating Token Index: 262

Text #3

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.1985. Min Act: -0.1700

Data Index: 1654787 (Python Code)

Max Activating Token Index: 455

Text #4

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.1985. Min Act: -0.1700

Data Index: 1523594 (Python Code)

Max Activating Token Index: 615

Text #5

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.1985. Min Act: -0.1700

Data Index: 1648033 (Python Code)

Max Activating Token Index: 712

Text #6

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.1985. Min Act: -0.1700

Data Index: 1385001 (Python Code)

Max Activating Token Index: 709

Text #7

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.2297. Min Act: -0.1700

Data Index: 1376044 (Python Code)

Max Activating Token Index: 484

Text #8

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.1672. Min Act: -0.1700

Data Index: 586831 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.1672. Min Act: -0.1700

Data Index: 1544773 (Python Code)

Max Activating Token Index: 734

Text #10

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.2610. Min Act: -0.1700

Data Index: 1521172 (Python Code)

Max Activating Token Index: 491

Text #11

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.1985. Min Act: -0.1700

Data Index: 1437507 (Python Code)

Max Activating Token Index: 445

Text #12

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.1672. Min Act: -0.1700

Data Index: 1452133 (Python Code)

Max Activating Token Index: 583

Text #13

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.1672. Min Act: -0.1700

Data Index: 1632690 (Python Code)

Max Activating Token Index: 424

Text #14

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.1360. Min Act: -0.1700

Data Index: 1458227 (Python Code)

Max Activating Token Index: 673

Text #15

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.1672. Min Act: -0.1700

Data Index: 1629063 (Python Code)

Max Activating Token Index: 349

Text #16

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.1360. Min Act: -0.1700

Data Index: 1523866 (Python Code)

Max Activating Token Index: 265

Text #17

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.1047. Min Act: -0.1700

Data Index: 1484051 (Python Code)

Max Activating Token Index: 368

Text #18

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.1985. Min Act: -0.1700

Data Index: 1454021 (Python Code)

Max Activating Token Index: 392

Text #19

Max Range: 5.6985. Min Range: -5.6985

Max Act: 5.1672. Min Act: -0.1700

Data Index: 1361403 (Python Code)

Max Activating Token Index: 549