Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 263 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.4606. Min Act: -0.1700

Data Index: 619297 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.3037. Min Act: -0.1700

Data Index: 672608 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.3351. Min Act: -0.1700

Data Index: 118212 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.3351. Min Act: -0.1700

Data Index: 685585 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.2723. Min Act: -0.1700

Data Index: 872882 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.3351. Min Act: -0.1700

Data Index: 63253 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.2723. Min Act: -0.1700

Data Index: 304868 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.2723. Min Act: -0.1700

Data Index: 1042895 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.2723. Min Act: -0.1700

Data Index: 287823 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.2723. Min Act: -0.1700

Data Index: 1224407 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.2723. Min Act: -0.1700

Data Index: 798235 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.3037. Min Act: -0.1700

Data Index: 1278682 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.3037. Min Act: -0.1700

Data Index: 253611 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.3037. Min Act: -0.1700

Data Index: 1341731 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.2409. Min Act: -0.1700

Data Index: 20263 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.2409. Min Act: -0.1700

Data Index: 40946 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.2409. Min Act: -0.1700

Data Index: 654764 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.2723. Min Act: -0.1700

Data Index: 335934 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.2094. Min Act: -0.1700

Data Index: 84903 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.2723. Min Act: -0.1700

Data Index: 562268 (C4 (Web Text))

Max Activating Token Index: 436