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

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

Neuron 1654 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.8490. Min Act: -0.1700

Data Index: 1448721 (Python Code)

Max Activating Token Index: 385

Text #1

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.8334. Min Act: -0.1700

Data Index: 1554792 (Python Code)

Max Activating Token Index: 755

Text #2

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.6300. Min Act: -0.1700

Data Index: 1364987 (Python Code)

Max Activating Token Index: 437

Text #3

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.5987. Min Act: -0.1700

Data Index: 1640691 (Python Code)

Max Activating Token Index: 527

Text #4

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.5830. Min Act: -0.1700

Data Index: 1511030 (Python Code)

Max Activating Token Index: 25

Text #5

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.5830. Min Act: -0.1700

Data Index: 1444297 (Python Code)

Max Activating Token Index: 567

Text #6

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.5517. Min Act: -0.1700

Data Index: 1518862 (Python Code)

Max Activating Token Index: 428

Text #7

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.5360. Min Act: -0.1700

Data Index: 1571465 (Python Code)

Max Activating Token Index: 963

Text #8

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.4890. Min Act: -0.1700

Data Index: 1435451 (Python Code)

Max Activating Token Index: 442

Text #9

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.4734. Min Act: -0.1700

Data Index: 1633063 (Python Code)

Max Activating Token Index: 43

Text #10

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.4734. Min Act: -0.1700

Data Index: 1371381 (Python Code)

Max Activating Token Index: 937

Text #11

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.4263. Min Act: -0.1700

Data Index: 1582025 (Python Code)

Max Activating Token Index: 382

Text #12

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.4734. Min Act: -0.1700

Data Index: 1596643 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.4420. Min Act: -0.1700

Data Index: 1530442 (Python Code)

Max Activating Token Index: 148

Text #14

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.4420. Min Act: -0.1700

Data Index: 1609534 (Python Code)

Max Activating Token Index: 304

Text #15

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.3950. Min Act: -0.1700

Data Index: 1604823 (Python Code)

Max Activating Token Index: 497

Text #16

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.3950. Min Act: -0.1700

Data Index: 1611575 (Python Code)

Max Activating Token Index: 297

Text #17

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.4107. Min Act: -0.1700

Data Index: 1463053 (Python Code)

Max Activating Token Index: 687

Text #18

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.3950. Min Act: -0.1700

Data Index: 1377380 (Python Code)

Max Activating Token Index: 42

Text #19

Max Range: 3.8490. Min Range: -3.8490

Max Act: 3.3793. Min Act: -0.1700

Data Index: 1458874 (Python Code)

Max Activating Token Index: 1023