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

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

Neuron 1317 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: 3.9289. Min Range: -3.9289

Max Act: 3.9289. Min Act: -0.1700

Data Index: 174452 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.9289. Min Range: -3.9289

Max Act: 3.8350. Min Act: -0.1700

Data Index: 1017691 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.9289. Min Range: -3.9289

Max Act: 3.6160. Min Act: -0.1700

Data Index: 502249 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.9289. Min Range: -3.9289

Max Act: 3.6786. Min Act: -0.1700

Data Index: 579438 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.9289. Min Range: -3.9289

Max Act: 3.6160. Min Act: -0.1700

Data Index: 205156 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 3.9289. Min Range: -3.9289

Max Act: 3.7099. Min Act: -0.1700

Data Index: 1180660 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.9289. Min Range: -3.9289

Max Act: 3.5534. Min Act: -0.1700

Data Index: 1311817 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.9289. Min Range: -3.9289

Max Act: 3.6160. Min Act: -0.1700

Data Index: 1106494 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.9289. Min Range: -3.9289

Max Act: 3.5847. Min Act: -0.1700

Data Index: 1172189 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.9289. Min Range: -3.9289

Max Act: 3.6160. Min Act: -0.1700

Data Index: 176375 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.9289. Min Range: -3.9289

Max Act: 3.5534. Min Act: -0.1700

Data Index: 559102 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.9289. Min Range: -3.9289

Max Act: 3.4907. Min Act: -0.1700

Data Index: 1512674 (Python Code)

Max Activating Token Index: 813

Text #12

Max Range: 3.9289. Min Range: -3.9289

Max Act: 3.4593. Min Act: -0.1700

Data Index: 1490036 (Python Code)

Max Activating Token Index: 822

Text #13

Max Range: 3.9289. Min Range: -3.9289

Max Act: 3.4907. Min Act: -0.1700

Data Index: 1485024 (Python Code)

Max Activating Token Index: 934

Text #14

Max Range: 3.9289. Min Range: -3.9289

Max Act: 3.5847. Min Act: -0.1700

Data Index: 1271389 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.9289. Min Range: -3.9289

Max Act: 3.4593. Min Act: -0.1700

Data Index: 350686 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 3.9289. Min Range: -3.9289

Max Act: 3.6160. Min Act: -0.1700

Data Index: 726242 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 3.9289. Min Range: -3.9289

Max Act: 3.4907. Min Act: -0.1700

Data Index: 899107 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.9289. Min Range: -3.9289

Max Act: 3.4907. Min Act: -0.1700

Data Index: 794724 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.9289. Min Range: -3.9289

Max Act: 3.5220. Min Act: -0.1700

Data Index: 152796 (C4 (Web Text))

Max Activating Token Index: 1023