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

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

Neuron 1019 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: 7.7866. Min Range: -7.7866

Max Act: 7.7866. Min Act: -0.1700

Data Index: 426336 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 7.7866. Min Range: -7.7866

Max Act: 7.6304. Min Act: -0.1700

Data Index: 963528 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 7.7866. Min Range: -7.7866

Max Act: 7.5679. Min Act: -0.1700

Data Index: 251733 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 7.7866. Min Range: -7.7866

Max Act: 7.5679. Min Act: -0.1700

Data Index: 436431 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 7.7866. Min Range: -7.7866

Max Act: 7.5054. Min Act: -0.1700

Data Index: 1278105 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 7.7866. Min Range: -7.7866

Max Act: 7.4429. Min Act: -0.1700

Data Index: 960138 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 7.7866. Min Range: -7.7866

Max Act: 7.4741. Min Act: -0.1700

Data Index: 812706 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 7.7866. Min Range: -7.7866

Max Act: 7.3491. Min Act: -0.1700

Data Index: 1349138 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 7.7866. Min Range: -7.7866

Max Act: 7.3491. Min Act: -0.1700

Data Index: 1233557 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 7.7866. Min Range: -7.7866

Max Act: 7.4116. Min Act: -0.1700

Data Index: 1016507 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 7.7866. Min Range: -7.7866

Max Act: 7.4429. Min Act: -0.1700

Data Index: 1232629 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 7.7866. Min Range: -7.7866

Max Act: 7.4116. Min Act: -0.1700

Data Index: 736331 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 7.7866. Min Range: -7.7866

Max Act: 7.3179. Min Act: -0.1700

Data Index: 238005 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 7.7866. Min Range: -7.7866

Max Act: 7.5054. Min Act: -0.1700

Data Index: 153508 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 7.7866. Min Range: -7.7866

Max Act: 7.2866. Min Act: -0.1700

Data Index: 890875 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 7.7866. Min Range: -7.7866

Max Act: 7.4116. Min Act: -0.1700

Data Index: 653995 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 7.7866. Min Range: -7.7866

Max Act: 7.3491. Min Act: -0.1700

Data Index: 1073026 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 7.7866. Min Range: -7.7866

Max Act: 7.4429. Min Act: -0.1700

Data Index: 972552 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 7.7866. Min Range: -7.7866

Max Act: 7.3804. Min Act: -0.1700

Data Index: 960153 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 7.7866. Min Range: -7.7866

Max Act: 7.3491. Min Act: -0.1700

Data Index: 337092 (C4 (Web Text))

Max Activating Token Index: 460