Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1657 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.3760. Min Act: -0.1700

Data Index: 1141174 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.2032. Min Act: -0.1700

Data Index: 419411 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.2346. Min Act: -0.1700

Data Index: 920100 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.3289. Min Act: -0.1700

Data Index: 667613 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.1402. Min Act: -0.1700

Data Index: 872281 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.1244. Min Act: -0.1700

Data Index: 1235978 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.0771. Min Act: -0.1700

Data Index: 895013 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.1087. Min Act: -0.1700

Data Index: 1108795 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.0771. Min Act: -0.1700

Data Index: 67828 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.1402. Min Act: -0.1700

Data Index: 800827 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.2032. Min Act: -0.1700

Data Index: 1065537 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.1244. Min Act: -0.1700

Data Index: 947444 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.1087. Min Act: -0.1700

Data Index: 97582 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.0929. Min Act: -0.1700

Data Index: 761768 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.0614. Min Act: -0.1700

Data Index: 335584 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.0929. Min Act: -0.1700

Data Index: 711976 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.0929. Min Act: -0.1700

Data Index: 620808 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.0614. Min Act: -0.1700

Data Index: 1055379 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.0929. Min Act: -0.1700

Data Index: 141937 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 3.3760. Min Range: -3.3760

Max Act: 3.0456. Min Act: -0.1700

Data Index: 1101790 (C4 (Web Text))

Max Activating Token Index: 938