Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 416 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.0031. Min Range: -3.0031

Max Act: 3.0031. Min Act: -0.1700

Data Index: 1102797 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.8923. Min Act: -0.1700

Data Index: 909749 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.8923. Min Act: -0.1700

Data Index: 837027 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.8764. Min Act: -0.1700

Data Index: 432808 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.8446. Min Act: -0.1700

Data Index: 742551 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.8287. Min Act: -0.1700

Data Index: 991712 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.8446. Min Act: -0.1700

Data Index: 463957 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.8446. Min Act: -0.1700

Data Index: 106185 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.7969. Min Act: -0.1700

Data Index: 158564 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.7809. Min Act: -0.1700

Data Index: 34738 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.7809. Min Act: -0.1700

Data Index: 1012051 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.7969. Min Act: -0.1700

Data Index: 98350 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.7809. Min Act: -0.1700

Data Index: 349996 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.7650. Min Act: -0.1700

Data Index: 1653631 (Python Code)

Max Activating Token Index: 20

Text #14

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.7490. Min Act: -0.1700

Data Index: 721228 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.7650. Min Act: -0.1700

Data Index: 715934 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.7650. Min Act: -0.1700

Data Index: 894751 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.7490. Min Act: -0.1700

Data Index: 597106 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.7490. Min Act: -0.1700

Data Index: 514099 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 3.0031. Min Range: -3.0031

Max Act: 2.7490. Min Act: -0.1700

Data Index: 124941 (C4 (Web Text))

Max Activating Token Index: 490