Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 495 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.3428. Min Range: -5.3428

Max Act: 5.2803. Min Act: -0.1700

Data Index: 660674 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 5.3428. Min Range: -5.3428

Max Act: 5.2803. Min Act: -0.1700

Data Index: 866403 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 5.3428. Min Range: -5.3428

Max Act: 5.3428. Min Act: -0.1700

Data Index: 1205952 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 5.3428. Min Range: -5.3428

Max Act: 5.2490. Min Act: -0.1700

Data Index: 397321 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 5.3428. Min Range: -5.3428

Max Act: 5.2178. Min Act: -0.1700

Data Index: 529686 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 5.3428. Min Range: -5.3428

Max Act: 5.2178. Min Act: -0.1700

Data Index: 762371 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 5.3428. Min Range: -5.3428

Max Act: 5.1865. Min Act: -0.1700

Data Index: 847853 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 5.3428. Min Range: -5.3428

Max Act: 5.1865. Min Act: -0.1700

Data Index: 193016 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 5.3428. Min Range: -5.3428

Max Act: 5.1240. Min Act: -0.1700

Data Index: 186511 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 5.3428. Min Range: -5.3428

Max Act: 5.0928. Min Act: -0.1700

Data Index: 308519 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 5.3428. Min Range: -5.3428

Max Act: 5.0928. Min Act: -0.1700

Data Index: 290011 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 5.3428. Min Range: -5.3428

Max Act: 5.0928. Min Act: -0.1700

Data Index: 432673 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 5.3428. Min Range: -5.3428

Max Act: 5.1240. Min Act: -0.1700

Data Index: 841414 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 5.3428. Min Range: -5.3428

Max Act: 5.0615. Min Act: -0.1700

Data Index: 193684 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 5.3428. Min Range: -5.3428

Max Act: 5.0303. Min Act: -0.1700

Data Index: 361254 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 5.3428. Min Range: -5.3428

Max Act: 5.0615. Min Act: -0.1700

Data Index: 569895 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 5.3428. Min Range: -5.3428

Max Act: 5.0615. Min Act: -0.1700

Data Index: 298084 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 5.3428. Min Range: -5.3428

Max Act: 4.9990. Min Act: -0.1700

Data Index: 504481 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 5.3428. Min Range: -5.3428

Max Act: 5.0615. Min Act: -0.1700

Data Index: 1300371 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 5.3428. Min Range: -5.3428

Max Act: 4.9990. Min Act: -0.1700

Data Index: 1055967 (C4 (Web Text))

Max Activating Token Index: 223