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

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

Neuron 836 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: 5.0904. Min Range: -5.0904

Max Act: 5.0904. Min Act: -0.1700

Data Index: 114020 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 5.0904. Min Range: -5.0904

Max Act: 4.9342. Min Act: -0.1700

Data Index: 353229 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 5.0904. Min Range: -5.0904

Max Act: 4.9654. Min Act: -0.1700

Data Index: 387963 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 5.0904. Min Range: -5.0904

Max Act: 4.9029. Min Act: -0.1700

Data Index: 820849 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 5.0904. Min Range: -5.0904

Max Act: 4.8404. Min Act: -0.1700

Data Index: 493590 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 5.0904. Min Range: -5.0904

Max Act: 4.8092. Min Act: -0.1700

Data Index: 1219790 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 5.0904. Min Range: -5.0904

Max Act: 4.8404. Min Act: -0.1700

Data Index: 854719 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 5.0904. Min Range: -5.0904

Max Act: 4.8092. Min Act: -0.1700

Data Index: 704918 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 5.0904. Min Range: -5.0904

Max Act: 4.8092. Min Act: -0.1699

Data Index: 300159 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 5.0904. Min Range: -5.0904

Max Act: 4.7779. Min Act: -0.1700

Data Index: 1308272 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 5.0904. Min Range: -5.0904

Max Act: 4.7779. Min Act: -0.1700

Data Index: 281992 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 5.0904. Min Range: -5.0904

Max Act: 4.7779. Min Act: -0.1700

Data Index: 465258 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 5.0904. Min Range: -5.0904

Max Act: 4.7467. Min Act: -0.1699

Data Index: 926374 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 5.0904. Min Range: -5.0904

Max Act: 4.6842. Min Act: -0.1700

Data Index: 32287 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 5.0904. Min Range: -5.0904

Max Act: 4.7467. Min Act: -0.1700

Data Index: 465119 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 5.0904. Min Range: -5.0904

Max Act: 4.6842. Min Act: -0.1700

Data Index: 250626 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 5.0904. Min Range: -5.0904

Max Act: 4.7467. Min Act: -0.1700

Data Index: 638661 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 5.0904. Min Range: -5.0904

Max Act: 4.6842. Min Act: -0.1700

Data Index: 401164 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 5.0904. Min Range: -5.0904

Max Act: 4.7154. Min Act: -0.1700

Data Index: 589935 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 5.0904. Min Range: -5.0904

Max Act: 4.6842. Min Act: -0.1700

Data Index: 878828 (C4 (Web Text))

Max Activating Token Index: 142