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

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

Neuron 1895 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: 3.0016. Min Range: -3.0016

Max Act: 3.0016. Min Act: -0.1700

Data Index: 1592271 (Python Code)

Max Activating Token Index: 597

Text #1

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.9884. Min Act: -0.1700

Data Index: 574249 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.9609. Min Act: -0.1700

Data Index: 271625 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.9175. Min Act: -0.1700

Data Index: 1389617 (Python Code)

Max Activating Token Index: 19

Text #4

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.9063. Min Act: -0.1700

Data Index: 30017 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8618. Min Act: -0.1700

Data Index: 950273 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8853. Min Act: -0.1700

Data Index: 1402990 (Python Code)

Max Activating Token Index: 17

Text #7

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8557. Min Act: -0.1700

Data Index: 640355 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8656. Min Act: -0.1700

Data Index: 1520704 (Python Code)

Max Activating Token Index: 333

Text #9

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8753. Min Act: -0.1700

Data Index: 190002 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8628. Min Act: -0.1700

Data Index: 888837 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8609. Min Act: -0.1700

Data Index: 854772 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8474. Min Act: -0.1700

Data Index: 1559610 (Python Code)

Max Activating Token Index: 665

Text #13

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8480. Min Act: -0.1700

Data Index: 1433071 (Python Code)

Max Activating Token Index: 671

Text #14

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8428. Min Act: -0.1700

Data Index: 1337217 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8309. Min Act: -0.1700

Data Index: 1021785 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8359. Min Act: -0.1700

Data Index: 786015 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8277. Min Act: -0.1700

Data Index: 1444834 (Python Code)

Max Activating Token Index: 25

Text #18

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8336. Min Act: -0.1700

Data Index: 1389081 (Python Code)

Max Activating Token Index: 449

Text #19

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8325. Min Act: -0.1700

Data Index: 633912 (C4 (Web Text))

Max Activating Token Index: 820