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

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

Neuron 577 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.9877. Min Act: -0.1700

Data Index: 392640 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.7689. Min Act: -0.1700

Data Index: 1132911 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.4252. Min Act: -0.1700

Data Index: 567999 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.3939. Min Act: -0.1700

Data Index: 909893 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.2064. Min Act: -0.1700

Data Index: 1127630 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.2689. Min Act: -0.1700

Data Index: 1288434 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.2689. Min Act: -0.1700

Data Index: 306518 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.3002. Min Act: -0.1700

Data Index: 1067691 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.2689. Min Act: -0.1700

Data Index: 1291621 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.3002. Min Act: -0.1700

Data Index: 693220 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.2689. Min Act: -0.1700

Data Index: 613018 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.1752. Min Act: -0.1700

Data Index: 791113 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.2064. Min Act: -0.1700

Data Index: 22361 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.1752. Min Act: -0.1700

Data Index: 715233 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.1752. Min Act: -0.1700

Data Index: 166200 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.1439. Min Act: -0.1700

Data Index: 576482 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.2377. Min Act: -0.1700

Data Index: 614567 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.2064. Min Act: -0.1700

Data Index: 578226 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.1439. Min Act: -0.1700

Data Index: 1015346 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 5.9877. Min Range: -5.9877

Max Act: 5.1752. Min Act: -0.1700

Data Index: 996686 (C4 (Web Text))

Max Activating Token Index: 756