Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1192 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.0868. Min Range: -3.0868

Max Act: 3.0868. Min Act: -0.1700

Data Index: 517213 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 3.0868. Min Range: -3.0868

Max Act: 3.0791. Min Act: -0.1700

Data Index: 92948 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 3.0868. Min Range: -3.0868

Max Act: 3.0759. Min Act: -0.1700

Data Index: 1025328 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 3.0868. Min Range: -3.0868

Max Act: 3.0503. Min Act: -0.1700

Data Index: 488771 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 3.0868. Min Range: -3.0868

Max Act: 3.0152. Min Act: -0.1700

Data Index: 933750 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 3.0868. Min Range: -3.0868

Max Act: 3.0231. Min Act: -0.1700

Data Index: 833147 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 3.0868. Min Range: -3.0868

Max Act: 2.9988. Min Act: -0.1700

Data Index: 1402134 (Python Code)

Max Activating Token Index: 507

Text #7

Max Range: 3.0868. Min Range: -3.0868

Max Act: 3.0061. Min Act: -0.1700

Data Index: 611752 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 3.0868. Min Range: -3.0868

Max Act: 3.0068. Min Act: -0.1700

Data Index: 1196828 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 3.0868. Min Range: -3.0868

Max Act: 3.0012. Min Act: -0.1700

Data Index: 277136 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 3.0868. Min Range: -3.0868

Max Act: 3.0024. Min Act: -0.1700

Data Index: 1608653 (Python Code)

Max Activating Token Index: 575

Text #11

Max Range: 3.0868. Min Range: -3.0868

Max Act: 2.9849. Min Act: -0.1700

Data Index: 1551687 (Python Code)

Max Activating Token Index: 285

Text #12

Max Range: 3.0868. Min Range: -3.0868

Max Act: 2.9738. Min Act: -0.1700

Data Index: 28626 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 3.0868. Min Range: -3.0868

Max Act: 2.9760. Min Act: -0.1700

Data Index: 1648876 (Python Code)

Max Activating Token Index: 620

Text #14

Max Range: 3.0868. Min Range: -3.0868

Max Act: 2.9684. Min Act: -0.1700

Data Index: 1626412 (Python Code)

Max Activating Token Index: 630

Text #15

Max Range: 3.0868. Min Range: -3.0868

Max Act: 2.9738. Min Act: -0.1700

Data Index: 763455 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 3.0868. Min Range: -3.0868

Max Act: 2.9806. Min Act: -0.1700

Data Index: 212667 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 3.0868. Min Range: -3.0868

Max Act: 2.9545. Min Act: -0.1700

Data Index: 1357120 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 3.0868. Min Range: -3.0868

Max Act: 2.9579. Min Act: -0.1700

Data Index: 704026 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 3.0868. Min Range: -3.0868

Max Act: 2.9598. Min Act: -0.1700

Data Index: 785878 (C4 (Web Text))

Max Activating Token Index: 587