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

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

Neuron 1629 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: 3.4640. Min Range: -3.4640

Max Act: 3.4640. Min Act: -0.1700

Data Index: 1311643 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.3386. Min Act: -0.1700

Data Index: 65914 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.3072. Min Act: -0.1700

Data Index: 1285750 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.2757. Min Act: -0.1700

Data Index: 942933 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.2129. Min Act: -0.1700

Data Index: 342070 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.1814. Min Act: -0.1700

Data Index: 973618 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.1184. Min Act: -0.1700

Data Index: 1313933 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.1499. Min Act: -0.1700

Data Index: 35833 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.1499. Min Act: -0.1700

Data Index: 589440 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.0553. Min Act: -0.1700

Data Index: 994840 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.1184. Min Act: -0.1700

Data Index: 12850 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.1184. Min Act: -0.1700

Data Index: 419023 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.1184. Min Act: -0.1700

Data Index: 1061789 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.0553. Min Act: -0.1700

Data Index: 401767 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.0237. Min Act: -0.1700

Data Index: 934265 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.0553. Min Act: -0.1700

Data Index: 58236 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.0869. Min Act: -0.1700

Data Index: 259100 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.0553. Min Act: -0.1700

Data Index: 1210370 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.0553. Min Act: -0.1700

Data Index: 549056 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.0237. Min Act: -0.1700

Data Index: 88825 (C4 (Web Text))

Max Activating Token Index: 671