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

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

Neuron 766 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.2479. Min Act: -0.1700

Data Index: 100020 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.2166. Min Act: -0.1700

Data Index: 492764 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.1541. Min Act: -0.1700

Data Index: 469829 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.1854. Min Act: -0.1700

Data Index: 783893 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.1854. Min Act: -0.1700

Data Index: 1273638 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.1854. Min Act: -0.1700

Data Index: 297654 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.1541. Min Act: -0.1700

Data Index: 271136 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.0916. Min Act: -0.1700

Data Index: 526670 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.0916. Min Act: -0.1700

Data Index: 942562 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.1541. Min Act: -0.1700

Data Index: 1257382 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.1229. Min Act: -0.1700

Data Index: 85267 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.1229. Min Act: -0.1700

Data Index: 638168 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.0916. Min Act: -0.1700

Data Index: 497787 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.1229. Min Act: -0.1699

Data Index: 98974 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.1229. Min Act: -0.1700

Data Index: 207478 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.1229. Min Act: -0.1700

Data Index: 569215 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.0916. Min Act: -0.1700

Data Index: 169002 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.0604. Min Act: -0.1700

Data Index: 466879 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.1229. Min Act: -0.1700

Data Index: 208834 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 5.2479. Min Range: -5.2479

Max Act: 5.1229. Min Act: -0.1700

Data Index: 342543 (C4 (Web Text))

Max Activating Token Index: 830