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

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

Neuron 1724 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.0938. Min Range: -3.0938

Max Act: 3.0938. Min Act: -0.1700

Data Index: 24670 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 3.0938. Min Range: -3.0938

Max Act: 3.0623. Min Act: -0.1700

Data Index: 1060417 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 3.0938. Min Range: -3.0938

Max Act: 3.0465. Min Act: -0.1700

Data Index: 788076 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 3.0938. Min Range: -3.0938

Max Act: 3.0465. Min Act: -0.1700

Data Index: 515680 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 3.0938. Min Range: -3.0938

Max Act: 3.0149. Min Act: -0.1700

Data Index: 910698 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 3.0938. Min Range: -3.0938

Max Act: 3.0307. Min Act: -0.1700

Data Index: 963188 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 3.0938. Min Range: -3.0938

Max Act: 3.0307. Min Act: -0.1700

Data Index: 648562 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 3.0938. Min Range: -3.0938

Max Act: 3.0149. Min Act: -0.1700

Data Index: 456555 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 3.0938. Min Range: -3.0938

Max Act: 2.9991. Min Act: -0.1700

Data Index: 476596 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 3.0938. Min Range: -3.0938

Max Act: 3.0149. Min Act: -0.1700

Data Index: 842201 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 3.0938. Min Range: -3.0938

Max Act: 3.0149. Min Act: -0.1700

Data Index: 152630 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 3.0938. Min Range: -3.0938

Max Act: 3.0307. Min Act: -0.1700

Data Index: 583854 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 3.0938. Min Range: -3.0938

Max Act: 3.0149. Min Act: -0.1700

Data Index: 1248564 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 3.0938. Min Range: -3.0938

Max Act: 3.0149. Min Act: -0.1700

Data Index: 185534 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 3.0938. Min Range: -3.0938

Max Act: 3.0149. Min Act: -0.1700

Data Index: 587796 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 3.0938. Min Range: -3.0938

Max Act: 3.0149. Min Act: -0.1700

Data Index: 492735 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 3.0938. Min Range: -3.0938

Max Act: 2.9991. Min Act: -0.1700

Data Index: 53653 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 3.0938. Min Range: -3.0938

Max Act: 2.9991. Min Act: -0.1700

Data Index: 443501 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 3.0938. Min Range: -3.0938

Max Act: 2.9833. Min Act: -0.1700

Data Index: 54775 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 3.0938. Min Range: -3.0938

Max Act: 2.9991. Min Act: -0.1700

Data Index: 802310 (C4 (Web Text))

Max Activating Token Index: 762