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

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

Neuron 579 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: 5.6052. Min Range: -5.6052

Max Act: 5.6052. Min Act: -0.1700

Data Index: 1591242 (Python Code)

Max Activating Token Index: 691

Text #1

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.4489. Min Act: -0.1700

Data Index: 1479343 (Python Code)

Max Activating Token Index: 829

Text #2

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.4177. Min Act: -0.1700

Data Index: 1641824 (Python Code)

Max Activating Token Index: 527

Text #3

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.4489. Min Act: -0.1700

Data Index: 1484656 (Python Code)

Max Activating Token Index: 864

Text #4

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.4177. Min Act: -0.1700

Data Index: 1585675 (Python Code)

Max Activating Token Index: 677

Text #5

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.3552. Min Act: -0.1700

Data Index: 1432226 (Python Code)

Max Activating Token Index: 299

Text #6

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.3864. Min Act: -0.1700

Data Index: 1420977 (Python Code)

Max Activating Token Index: 833

Text #7

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.3864. Min Act: -0.1700

Data Index: 1564427 (Python Code)

Max Activating Token Index: 391

Text #8

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.3864. Min Act: -0.1700

Data Index: 1591349 (Python Code)

Max Activating Token Index: 538

Text #9

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.3239. Min Act: -0.1700

Data Index: 1502000 (Python Code)

Max Activating Token Index: 266

Text #10

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.3552. Min Act: -0.1700

Data Index: 1392807 (Python Code)

Max Activating Token Index: 229

Text #11

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.3552. Min Act: -0.1700

Data Index: 1366313 (Python Code)

Max Activating Token Index: 880

Text #12

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.3239. Min Act: -0.1700

Data Index: 1645693 (Python Code)

Max Activating Token Index: 654

Text #13

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.3552. Min Act: -0.1700

Data Index: 1422904 (Python Code)

Max Activating Token Index: 425

Text #14

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.3239. Min Act: -0.1700

Data Index: 1363114 (Python Code)

Max Activating Token Index: 315

Text #15

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.2927. Min Act: -0.1700

Data Index: 1579813 (Python Code)

Max Activating Token Index: 171

Text #16

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.2614. Min Act: -0.1700

Data Index: 1444450 (Python Code)

Max Activating Token Index: 686

Text #17

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.2927. Min Act: -0.1700

Data Index: 1433453 (Python Code)

Max Activating Token Index: 337

Text #18

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.2927. Min Act: -0.1700

Data Index: 1423168 (Python Code)

Max Activating Token Index: 849

Text #19

Max Range: 5.6052. Min Range: -5.6052

Max Act: 5.3239. Min Act: -0.1700

Data Index: 1489448 (Python Code)

Max Activating Token Index: 303