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

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

Neuron 1121 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: 3.7841. Min Range: -3.7841

Max Act: 3.7841. Min Act: -0.1700

Data Index: 949687 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.7579. Min Act: -0.1700

Data Index: 534453 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.7746. Min Act: -0.1700

Data Index: 754288 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.7442. Min Act: -0.1700

Data Index: 1022962 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.7492. Min Act: -0.1700

Data Index: 230226 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.7428. Min Act: -0.1700

Data Index: 1119835 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.7268. Min Act: -0.1700

Data Index: 1241213 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.7230. Min Act: -0.1700

Data Index: 1257529 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6785. Min Act: -0.1700

Data Index: 26310 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6673. Min Act: -0.1700

Data Index: 513816 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6748. Min Act: -0.1700

Data Index: 1223892 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6539. Min Act: -0.1700

Data Index: 90721 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6506. Min Act: -0.1700

Data Index: 684199 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6051. Min Act: -0.1700

Data Index: 727439 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6095. Min Act: -0.1700

Data Index: 419139 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.5844. Min Act: -0.1700

Data Index: 796162 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.5657. Min Act: -0.1700

Data Index: 226469 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.5844. Min Act: -0.1700

Data Index: 1166388 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.5743. Min Act: -0.1700

Data Index: 340516 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.5646. Min Act: -0.1654

Data Index: 720055 (C4 (Web Text))

Max Activating Token Index: 377