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

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

Neuron 1651 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: 5.2912. Min Range: -5.2912

Max Act: 5.2174. Min Act: -0.1700

Data Index: 367976 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 5.2912. Min Range: -5.2912

Max Act: 5.2912. Min Act: -0.1700

Data Index: 124469 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 5.2912. Min Range: -5.2912

Max Act: 5.1783. Min Act: -0.1700

Data Index: 1483088 (Python Code)

Max Activating Token Index: 673

Text #3

Max Range: 5.2912. Min Range: -5.2912

Max Act: 5.1382. Min Act: -0.1700

Data Index: 468608 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 5.2912. Min Range: -5.2912

Max Act: 5.0743. Min Act: -0.1700

Data Index: 95956 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 5.2912. Min Range: -5.2912

Max Act: 5.0153. Min Act: -0.1700

Data Index: 743696 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 5.2912. Min Range: -5.2912

Max Act: 5.0402. Min Act: -0.1700

Data Index: 428281 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 5.2912. Min Range: -5.2912

Max Act: 5.0179. Min Act: -0.1700

Data Index: 379780 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 5.2912. Min Range: -5.2912

Max Act: 5.0357. Min Act: -0.1700

Data Index: 977391 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 5.2912. Min Range: -5.2912

Max Act: 4.9284. Min Act: -0.1700

Data Index: 199888 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 5.2912. Min Range: -5.2912

Max Act: 5.0016. Min Act: -0.1700

Data Index: 350792 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 5.2912. Min Range: -5.2912

Max Act: 5.0222. Min Act: -0.1700

Data Index: 443391 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 5.2912. Min Range: -5.2912

Max Act: 4.9722. Min Act: -0.1700

Data Index: 932470 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 5.2912. Min Range: -5.2912

Max Act: 4.9147. Min Act: -0.1700

Data Index: 147163 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 5.2912. Min Range: -5.2912

Max Act: 4.9714. Min Act: -0.1700

Data Index: 33683 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 5.2912. Min Range: -5.2912

Max Act: 4.9502. Min Act: -0.1700

Data Index: 1016787 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 5.2912. Min Range: -5.2912

Max Act: 4.9795. Min Act: -0.1700

Data Index: 140306 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 5.2912. Min Range: -5.2912

Max Act: 4.9314. Min Act: -0.1700

Data Index: 98856 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 5.2912. Min Range: -5.2912

Max Act: 5.0300. Min Act: -0.1700

Data Index: 183227 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 5.2912. Min Range: -5.2912

Max Act: 4.9797. Min Act: -0.1700

Data Index: 756354 (C4 (Web Text))

Max Activating Token Index: 212