Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1139 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.9219. Min Act: -0.1700

Data Index: 860272 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8847. Min Act: -0.1700

Data Index: 914162 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8740. Min Act: -0.1700

Data Index: 1610680 (Python Code)

Max Activating Token Index: 612

Text #3

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8597. Min Act: -0.1700

Data Index: 140842 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.8416. Min Act: -0.1700

Data Index: 304359 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.7591. Min Act: -0.1700

Data Index: 490142 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.7699. Min Act: -0.1700

Data Index: 1525553 (Python Code)

Max Activating Token Index: 764

Text #7

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.7573. Min Act: -0.1700

Data Index: 1378361 (Python Code)

Max Activating Token Index: 526

Text #8

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.7513. Min Act: -0.1700

Data Index: 384775 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.7347. Min Act: -0.1700

Data Index: 1462918 (Python Code)

Max Activating Token Index: 285

Text #10

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.7406. Min Act: -0.1700

Data Index: 1444656 (Python Code)

Max Activating Token Index: 137

Text #11

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.7507. Min Act: -0.1700

Data Index: 596211 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.7478. Min Act: -0.1700

Data Index: 420930 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.7308. Min Act: -0.1700

Data Index: 980475 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.7327. Min Act: -0.1700

Data Index: 1548365 (Python Code)

Max Activating Token Index: 80

Text #15

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.7376. Min Act: -0.1700

Data Index: 533819 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.7103. Min Act: -0.1700

Data Index: 1362347 (Python Code)

Max Activating Token Index: 51

Text #17

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.7136. Min Act: -0.1700

Data Index: 1446240 (Python Code)

Max Activating Token Index: 40

Text #18

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.7246. Min Act: -0.1700

Data Index: 1460061 (Python Code)

Max Activating Token Index: 227

Text #19

Max Range: 2.9219. Min Range: -2.9219

Max Act: 2.7162. Min Act: -0.1700

Data Index: 1619966 (Python Code)

Max Activating Token Index: 6