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

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

Neuron 735 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: 4.0506. Min Range: -4.0506

Max Act: 4.0506. Min Act: -0.1700

Data Index: 635724 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 4.0506. Min Range: -4.0506

Max Act: 4.0193. Min Act: -0.1700

Data Index: 524231 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 4.0506. Min Range: -4.0506

Max Act: 4.0193. Min Act: -0.1700

Data Index: 925776 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 4.0506. Min Range: -4.0506

Max Act: 4.0193. Min Act: -0.1700

Data Index: 1179330 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 4.0506. Min Range: -4.0506

Max Act: 3.9880. Min Act: -0.1700

Data Index: 436657 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 4.0506. Min Range: -4.0506

Max Act: 3.9255. Min Act: -0.1700

Data Index: 592342 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 4.0506. Min Range: -4.0506

Max Act: 3.9568. Min Act: -0.1700

Data Index: 1234551 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 4.0506. Min Range: -4.0506

Max Act: 3.9255. Min Act: -0.1700

Data Index: 880806 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 4.0506. Min Range: -4.0506

Max Act: 3.9568. Min Act: -0.1700

Data Index: 1233720 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 4.0506. Min Range: -4.0506

Max Act: 3.8942. Min Act: -0.1700

Data Index: 240175 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 4.0506. Min Range: -4.0506

Max Act: 3.8629. Min Act: -0.1700

Data Index: 402094 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 4.0506. Min Range: -4.0506

Max Act: 3.8317. Min Act: -0.1700

Data Index: 1109290 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 4.0506. Min Range: -4.0506

Max Act: 3.9255. Min Act: -0.1700

Data Index: 1223827 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 4.0506. Min Range: -4.0506

Max Act: 3.8942. Min Act: -0.1700

Data Index: 50512 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 4.0506. Min Range: -4.0506

Max Act: 3.8317. Min Act: -0.1700

Data Index: 1307857 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 4.0506. Min Range: -4.0506

Max Act: 3.8317. Min Act: -0.1700

Data Index: 288498 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 4.0506. Min Range: -4.0506

Max Act: 3.8629. Min Act: -0.1700

Data Index: 631878 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 4.0506. Min Range: -4.0506

Max Act: 3.8317. Min Act: -0.1700

Data Index: 736338 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 4.0506. Min Range: -4.0506

Max Act: 3.8317. Min Act: -0.1700

Data Index: 270746 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 4.0506. Min Range: -4.0506

Max Act: 3.8317. Min Act: -0.1700

Data Index: 925280 (C4 (Web Text))

Max Activating Token Index: 930