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

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

Neuron 1214 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.3965. Min Act: -0.1700

Data Index: 460393 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.3808. Min Act: -0.1700

Data Index: 523814 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.3808. Min Act: -0.1700

Data Index: 951458 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.3494. Min Act: -0.1700

Data Index: 195274 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.3338. Min Act: -0.1700

Data Index: 1109930 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.3494. Min Act: -0.1700

Data Index: 1056497 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.3338. Min Act: -0.1700

Data Index: 1034293 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.3023. Min Act: -0.1700

Data Index: 698767 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.2709. Min Act: -0.1700

Data Index: 1242981 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.2709. Min Act: -0.1700

Data Index: 417746 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.2552. Min Act: -0.1700

Data Index: 145443 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.2552. Min Act: -0.1700

Data Index: 1026628 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.2552. Min Act: -0.1700

Data Index: 362097 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.2552. Min Act: -0.1700

Data Index: 1228162 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.2395. Min Act: -0.1700

Data Index: 838062 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.2238. Min Act: -0.1700

Data Index: 475638 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.2238. Min Act: -0.1700

Data Index: 29663 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.2080. Min Act: -0.1700

Data Index: 52305 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.1923. Min Act: -0.1700

Data Index: 252817 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 3.3965. Min Range: -3.3965

Max Act: 3.1766. Min Act: -0.1700

Data Index: 1095635 (C4 (Web Text))

Max Activating Token Index: 614