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

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

Neuron 652 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: 3.5182. Min Range: -3.5182

Max Act: 3.5182. Min Act: -0.1700

Data Index: 1151093 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 3.5182. Min Range: -3.5182

Max Act: 3.4985. Min Act: -0.1700

Data Index: 1104560 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 3.5182. Min Range: -3.5182

Max Act: 3.4748. Min Act: -0.1700

Data Index: 1179551 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 3.5182. Min Range: -3.5182

Max Act: 3.4129. Min Act: -0.1700

Data Index: 368781 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 3.5182. Min Range: -3.5182

Max Act: 3.4195. Min Act: -0.1700

Data Index: 754576 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 3.5182. Min Range: -3.5182

Max Act: 3.3784. Min Act: -0.1700

Data Index: 743606 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 3.5182. Min Range: -3.5182

Max Act: 3.3673. Min Act: -0.1700

Data Index: 276719 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 3.5182. Min Range: -3.5182

Max Act: 3.3583. Min Act: -0.1700

Data Index: 349472 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 3.5182. Min Range: -3.5182

Max Act: 3.3453. Min Act: -0.1700

Data Index: 26550 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 3.5182. Min Range: -3.5182

Max Act: 3.3641. Min Act: -0.1700

Data Index: 1069196 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 3.5182. Min Range: -3.5182

Max Act: 3.3415. Min Act: -0.1700

Data Index: 1308269 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 3.5182. Min Range: -3.5182

Max Act: 3.3267. Min Act: -0.1700

Data Index: 878901 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 3.5182. Min Range: -3.5182

Max Act: 3.3187. Min Act: -0.1700

Data Index: 255208 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 3.5182. Min Range: -3.5182

Max Act: 3.3328. Min Act: -0.1700

Data Index: 1023752 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 3.5182. Min Range: -3.5182

Max Act: 3.3274. Min Act: -0.1700

Data Index: 1213991 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 3.5182. Min Range: -3.5182

Max Act: 3.3292. Min Act: -0.1700

Data Index: 919676 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 3.5182. Min Range: -3.5182

Max Act: 3.3057. Min Act: -0.1700

Data Index: 1189139 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 3.5182. Min Range: -3.5182

Max Act: 3.3274. Min Act: -0.1700

Data Index: 883732 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 3.5182. Min Range: -3.5182

Max Act: 3.3285. Min Act: -0.1700

Data Index: 854108 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 3.5182. Min Range: -3.5182

Max Act: 3.2983. Min Act: -0.1700

Data Index: 1139527 (C4 (Web Text))

Max Activating Token Index: 570