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

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

Neuron 713 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: 3.3856. Min Range: -3.3856

Max Act: 3.3856. Min Act: -0.1700

Data Index: 802410 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.3542. Min Act: -0.1700

Data Index: 53808 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.3699. Min Act: -0.1700

Data Index: 956906 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2600. Min Act: -0.1700

Data Index: 1568928 (Python Code)

Max Activating Token Index: 556

Text #4

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2600. Min Act: -0.1700

Data Index: 293506 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2757. Min Act: -0.1700

Data Index: 240716 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2914. Min Act: -0.1700

Data Index: 1345021 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2600. Min Act: -0.1700

Data Index: 66084 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2285. Min Act: -0.1700

Data Index: 275397 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1971. Min Act: -0.1700

Data Index: 138460 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2285. Min Act: -0.1700

Data Index: 373552 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2757. Min Act: -0.1700

Data Index: 990369 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1971. Min Act: -0.1700

Data Index: 163297 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1814. Min Act: -0.1700

Data Index: 407683 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1971. Min Act: -0.1700

Data Index: 269759 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1814. Min Act: -0.1700

Data Index: 1107703 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1814. Min Act: -0.1700

Data Index: 391911 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2285. Min Act: -0.1700

Data Index: 891177 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2285. Min Act: -0.1700

Data Index: 602153 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1656. Min Act: -0.1700

Data Index: 1230843 (C4 (Web Text))

Max Activating Token Index: 630