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

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

Neuron 571 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: 7.1024. Min Range: -7.1024

Max Act: 7.1024. Min Act: -0.1700

Data Index: 812246 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 7.1024. Min Range: -7.1024

Max Act: 6.6962. Min Act: -0.1700

Data Index: 813562 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 7.1024. Min Range: -7.1024

Max Act: 6.7274. Min Act: -0.1700

Data Index: 283015 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 7.1024. Min Range: -7.1024

Max Act: 6.8524. Min Act: -0.1700

Data Index: 777991 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 7.1024. Min Range: -7.1024

Max Act: 6.7274. Min Act: -0.1700

Data Index: 1224057 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 7.1024. Min Range: -7.1024

Max Act: 6.7274. Min Act: -0.1700

Data Index: 592549 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 7.1024. Min Range: -7.1024

Max Act: 6.7274. Min Act: -0.1700

Data Index: 1163210 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 7.1024. Min Range: -7.1024

Max Act: 6.5712. Min Act: -0.1700

Data Index: 961482 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 7.1024. Min Range: -7.1024

Max Act: 6.5712. Min Act: -0.1700

Data Index: 1155231 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 7.1024. Min Range: -7.1024

Max Act: 6.3837. Min Act: -0.1700

Data Index: 659292 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 7.1024. Min Range: -7.1024

Max Act: 6.4774. Min Act: -0.1700

Data Index: 482225 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 7.1024. Min Range: -7.1024

Max Act: 6.4149. Min Act: -0.1700

Data Index: 12778 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 7.1024. Min Range: -7.1024

Max Act: 6.3212. Min Act: -0.1700

Data Index: 555099 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 7.1024. Min Range: -7.1024

Max Act: 6.3212. Min Act: -0.1700

Data Index: 1291679 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 7.1024. Min Range: -7.1024

Max Act: 6.4462. Min Act: -0.1700

Data Index: 828993 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 7.1024. Min Range: -7.1024

Max Act: 6.3837. Min Act: -0.1700

Data Index: 275902 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 7.1024. Min Range: -7.1024

Max Act: 6.2587. Min Act: -0.1700

Data Index: 1218461 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 7.1024. Min Range: -7.1024

Max Act: 6.1962. Min Act: -0.1700

Data Index: 749039 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 7.1024. Min Range: -7.1024

Max Act: 6.0399. Min Act: -0.1700

Data Index: 565949 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 7.1024. Min Range: -7.1024

Max Act: 6.1649. Min Act: -0.1700

Data Index: 39499 (C4 (Web Text))

Max Activating Token Index: 73