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

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

Neuron 394 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: 5.1001. Min Range: -5.1001

Max Act: 5.1001. Min Act: -0.1700

Data Index: 1030819 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8814. Min Act: -0.1700

Data Index: 288590 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8814. Min Act: -0.1700

Data Index: 943099 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8814. Min Act: -0.1700

Data Index: 418807 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8814. Min Act: -0.1700

Data Index: 912866 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8814. Min Act: -0.1700

Data Index: 1026998 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8501. Min Act: -0.1700

Data Index: 279712 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8189. Min Act: -0.1700

Data Index: 955567 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.9126. Min Act: -0.1700

Data Index: 730639 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.7564. Min Act: -0.1700

Data Index: 1053408 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8189. Min Act: -0.1700

Data Index: 871399 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8189. Min Act: -0.1700

Data Index: 1038815 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8501. Min Act: -0.1700

Data Index: 123904 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8189. Min Act: -0.1700

Data Index: 1044326 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8501. Min Act: -0.1700

Data Index: 955184 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8189. Min Act: -0.1700

Data Index: 520767 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.7876. Min Act: -0.1700

Data Index: 90999 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.7564. Min Act: -0.1700

Data Index: 132131 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.7564. Min Act: -0.1700

Data Index: 200112 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.7564. Min Act: -0.1700

Data Index: 515385 (C4 (Web Text))

Max Activating Token Index: 980