Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1990 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.2157. Min Range: -4.2157

Max Act: 4.2157. Min Act: -0.1700

Data Index: 842744 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 4.2157. Min Range: -4.2157

Max Act: 4.0787. Min Act: -0.1700

Data Index: 186362 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 4.2157. Min Range: -4.2157

Max Act: 4.0521. Min Act: -0.1700

Data Index: 763344 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 4.2157. Min Range: -4.2157

Max Act: 4.0063. Min Act: -0.1700

Data Index: 737820 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 4.2157. Min Range: -4.2157

Max Act: 4.0217. Min Act: -0.1700

Data Index: 414608 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 4.2157. Min Range: -4.2157

Max Act: 3.9820. Min Act: -0.1700

Data Index: 1282813 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 4.2157. Min Range: -4.2157

Max Act: 3.9786. Min Act: -0.1700

Data Index: 985868 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 4.2157. Min Range: -4.2157

Max Act: 3.9868. Min Act: -0.1700

Data Index: 1339873 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 4.2157. Min Range: -4.2157

Max Act: 3.9746. Min Act: -0.1700

Data Index: 1077811 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 4.2157. Min Range: -4.2157

Max Act: 3.9436. Min Act: -0.1700

Data Index: 1263702 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 4.2157. Min Range: -4.2157

Max Act: 3.9429. Min Act: -0.1700

Data Index: 1150563 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 4.2157. Min Range: -4.2157

Max Act: 3.9589. Min Act: -0.1700

Data Index: 344889 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 4.2157. Min Range: -4.2157

Max Act: 3.9453. Min Act: -0.1700

Data Index: 1181627 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 4.2157. Min Range: -4.2157

Max Act: 3.9530. Min Act: -0.1700

Data Index: 1277642 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 4.2157. Min Range: -4.2157

Max Act: 3.9370. Min Act: -0.1700

Data Index: 164432 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 4.2157. Min Range: -4.2157

Max Act: 3.9061. Min Act: -0.1700

Data Index: 764037 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 4.2157. Min Range: -4.2157

Max Act: 3.9184. Min Act: -0.1700

Data Index: 16762 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 4.2157. Min Range: -4.2157

Max Act: 3.9195. Min Act: -0.1700

Data Index: 206984 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 4.2157. Min Range: -4.2157

Max Act: 3.9071. Min Act: -0.1700

Data Index: 567937 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 4.2157. Min Range: -4.2157

Max Act: 3.9080. Min Act: -0.1700

Data Index: 63219 (C4 (Web Text))

Max Activating Token Index: 460