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

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

Neuron 1848 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: 4.1547. Min Range: -4.1547

Max Act: 4.1547. Min Act: -0.1700

Data Index: 1527746 (Python Code)

Max Activating Token Index: 721

Text #1

Max Range: 4.1547. Min Range: -4.1547

Max Act: 3.9918. Min Act: -0.0588

Data Index: 1502027 (Python Code)

Max Activating Token Index: 127

Text #2

Max Range: 4.1547. Min Range: -4.1547

Max Act: 3.8868. Min Act: -0.1699

Data Index: 1080047 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 4.1547. Min Range: -4.1547

Max Act: 3.8814. Min Act: -0.1700

Data Index: 474125 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 4.1547. Min Range: -4.1547

Max Act: 3.8932. Min Act: -0.1700

Data Index: 959309 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 4.1547. Min Range: -4.1547

Max Act: 3.8409. Min Act: -0.1575

Data Index: 1587407 (Python Code)

Max Activating Token Index: 99

Text #6

Max Range: 4.1547. Min Range: -4.1547

Max Act: 3.8564. Min Act: -0.1700

Data Index: 1649360 (Python Code)

Max Activating Token Index: 783

Text #7

Max Range: 4.1547. Min Range: -4.1547

Max Act: 3.8345. Min Act: -0.1698

Data Index: 1368850 (Python Code)

Max Activating Token Index: 147

Text #8

Max Range: 4.1547. Min Range: -4.1547

Max Act: 3.8024. Min Act: -0.1346

Data Index: 1650907 (Python Code)

Max Activating Token Index: 181

Text #9

Max Range: 4.1547. Min Range: -4.1547

Max Act: 3.7847. Min Act: -0.1699

Data Index: 1380023 (Python Code)

Max Activating Token Index: 780

Text #10

Max Range: 4.1547. Min Range: -4.1547

Max Act: 3.7490. Min Act: -0.0463

Data Index: 1515365 (Python Code)

Max Activating Token Index: 863

Text #11

Max Range: 4.1547. Min Range: -4.1547

Max Act: 3.7630. Min Act: -0.1640

Data Index: 1384193 (Python Code)

Max Activating Token Index: 353

Text #12

Max Range: 4.1547. Min Range: -4.1547

Max Act: 3.7425. Min Act: -0.1700

Data Index: 1474335 (Python Code)

Max Activating Token Index: 793

Text #13

Max Range: 4.1547. Min Range: -4.1547

Max Act: 3.7233. Min Act: -0.1699

Data Index: 1449342 (Python Code)

Max Activating Token Index: 898

Text #14

Max Range: 4.1547. Min Range: -4.1547

Max Act: 3.6866. Min Act: -0.1697

Data Index: 1582638 (Python Code)

Max Activating Token Index: 632

Text #15

Max Range: 4.1547. Min Range: -4.1547

Max Act: 3.7054. Min Act: -0.1672

Data Index: 1569825 (Python Code)

Max Activating Token Index: 424

Text #16

Max Range: 4.1547. Min Range: -4.1547

Max Act: 3.6869. Min Act: -0.1689

Data Index: 1627149 (Python Code)

Max Activating Token Index: 1009

Text #17

Max Range: 4.1547. Min Range: -4.1547

Max Act: 3.6772. Min Act: -0.1693

Data Index: 1414186 (Python Code)

Max Activating Token Index: 758

Text #18

Max Range: 4.1547. Min Range: -4.1547

Max Act: 3.6597. Min Act: -0.0999

Data Index: 1596764 (Python Code)

Max Activating Token Index: 259

Text #19

Max Range: 4.1547. Min Range: -4.1547

Max Act: 3.6638. Min Act: -0.1700

Data Index: 1426075 (Python Code)

Max Activating Token Index: 610