Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 157 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.8752. Min Act: -0.1700

Data Index: 694939 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.8439. Min Act: -0.1700

Data Index: 653176 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.7188. Min Act: -0.1700

Data Index: 1227101 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6875. Min Act: -0.1700

Data Index: 277049 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6875. Min Act: -0.1700

Data Index: 535860 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6249. Min Act: -0.1700

Data Index: 1053157 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6718. Min Act: -0.1700

Data Index: 1338882 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6562. Min Act: -0.1700

Data Index: 97708 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.5935. Min Act: -0.1700

Data Index: 805082 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6249. Min Act: -0.1700

Data Index: 689818 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6562. Min Act: -0.1700

Data Index: 1341192 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6562. Min Act: -0.1700

Data Index: 457587 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6405. Min Act: -0.1700

Data Index: 277813 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6405. Min Act: -0.1700

Data Index: 695093 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6405. Min Act: -0.1700

Data Index: 310391 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6562. Min Act: -0.1700

Data Index: 251224 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6249. Min Act: -0.1700

Data Index: 461092 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6249. Min Act: -0.1700

Data Index: 887737 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6092. Min Act: -0.1700

Data Index: 607973 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.5779. Min Act: -0.1700

Data Index: 792889 (C4 (Web Text))

Max Activating Token Index: 158