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

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

Neuron 1558 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: 3.5458. Min Range: -3.5458

Max Act: 3.5458. Min Act: -0.1700

Data Index: 1126312 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 3.5458. Min Range: -3.5458

Max Act: 3.4518. Min Act: -0.1700

Data Index: 271781 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 3.5458. Min Range: -3.5458

Max Act: 3.4518. Min Act: -0.1700

Data Index: 1057091 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 3.5458. Min Range: -3.5458

Max Act: 3.3263. Min Act: -0.1700

Data Index: 622207 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 3.5458. Min Range: -3.5458

Max Act: 3.3263. Min Act: -0.1700

Data Index: 25529 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.5458. Min Range: -3.5458

Max Act: 3.3577. Min Act: -0.1700

Data Index: 522968 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 3.5458. Min Range: -3.5458

Max Act: 3.3577. Min Act: -0.1700

Data Index: 909356 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 3.5458. Min Range: -3.5458

Max Act: 3.3577. Min Act: -0.1700

Data Index: 349754 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 3.5458. Min Range: -3.5458

Max Act: 3.3263. Min Act: -0.1700

Data Index: 170626 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 3.5458. Min Range: -3.5458

Max Act: 3.3263. Min Act: -0.1700

Data Index: 462667 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 3.5458. Min Range: -3.5458

Max Act: 3.2949. Min Act: -0.1700

Data Index: 333177 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 3.5458. Min Range: -3.5458

Max Act: 3.2949. Min Act: -0.1700

Data Index: 1179993 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.5458. Min Range: -3.5458

Max Act: 3.3263. Min Act: -0.1700

Data Index: 33649 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 3.5458. Min Range: -3.5458

Max Act: 3.2949. Min Act: -0.1700

Data Index: 1123918 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 3.5458. Min Range: -3.5458

Max Act: 3.2320. Min Act: -0.1700

Data Index: 68994 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 3.5458. Min Range: -3.5458

Max Act: 3.2634. Min Act: -0.1700

Data Index: 18259 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 3.5458. Min Range: -3.5458

Max Act: 3.2634. Min Act: -0.1700

Data Index: 1153456 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 3.5458. Min Range: -3.5458

Max Act: 3.2634. Min Act: -0.1700

Data Index: 189403 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 3.5458. Min Range: -3.5458

Max Act: 3.2634. Min Act: -0.1700

Data Index: 1067760 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 3.5458. Min Range: -3.5458

Max Act: 3.2320. Min Act: -0.1700

Data Index: 637020 (C4 (Web Text))

Max Activating Token Index: 268