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

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

Neuron 554 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.7112. Min Act: -0.1700

Data Index: 1409847 (Python Code)

Max Activating Token Index: 779

Text #1

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.6799. Min Act: -0.1700

Data Index: 1236712 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.6486. Min Act: -0.1700

Data Index: 860663 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.6486. Min Act: -0.1700

Data Index: 1540562 (Python Code)

Max Activating Token Index: 453

Text #4

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.6173. Min Act: -0.1700

Data Index: 1389243 (Python Code)

Max Activating Token Index: 542

Text #5

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.6173. Min Act: -0.1700

Data Index: 1493903 (Python Code)

Max Activating Token Index: 590

Text #6

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.5703. Min Act: -0.1700

Data Index: 1376568 (Python Code)

Max Activating Token Index: 735

Text #7

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.6016. Min Act: -0.1700

Data Index: 1540882 (Python Code)

Max Activating Token Index: 512

Text #8

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.6329. Min Act: -0.1700

Data Index: 1381611 (Python Code)

Max Activating Token Index: 432

Text #9

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.6173. Min Act: -0.1700

Data Index: 1655203 (Python Code)

Max Activating Token Index: 623

Text #10

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.6016. Min Act: -0.1700

Data Index: 1366448 (Python Code)

Max Activating Token Index: 338

Text #11

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.6016. Min Act: -0.1700

Data Index: 1465995 (Python Code)

Max Activating Token Index: 289

Text #12

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.5860. Min Act: -0.1700

Data Index: 1623873 (Python Code)

Max Activating Token Index: 391

Text #13

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.6016. Min Act: -0.1700

Data Index: 121183 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.6016. Min Act: -0.1700

Data Index: 1579995 (Python Code)

Max Activating Token Index: 608

Text #15

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.6173. Min Act: -0.1700

Data Index: 1577924 (Python Code)

Max Activating Token Index: 362

Text #16

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.5860. Min Act: -0.1700

Data Index: 1648859 (Python Code)

Max Activating Token Index: 462

Text #17

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.5703. Min Act: -0.1700

Data Index: 1416554 (Python Code)

Max Activating Token Index: 675

Text #18

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.5860. Min Act: -0.1700

Data Index: 1395109 (Python Code)

Max Activating Token Index: 389

Text #19

Max Range: 3.7112. Min Range: -3.7112

Max Act: 3.6016. Min Act: -0.1700

Data Index: 1468626 (Python Code)

Max Activating Token Index: 342