Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1353 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.8530. Min Act: -0.1700

Data Index: 763953 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.5713. Min Act: -0.1700

Data Index: 413722 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.5713. Min Act: -0.1700

Data Index: 1654530 (Python Code)

Max Activating Token Index: 247

Text #3

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.5713. Min Act: -0.1700

Data Index: 1638136 (Python Code)

Max Activating Token Index: 59

Text #4

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.5557. Min Act: -0.1700

Data Index: 1458326 (Python Code)

Max Activating Token Index: 64

Text #5

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.5713. Min Act: -0.1700

Data Index: 1454667 (Python Code)

Max Activating Token Index: 58

Text #6

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.5243. Min Act: -0.1700

Data Index: 1084654 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.4773. Min Act: -0.1700

Data Index: 335592 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.5243. Min Act: -0.1700

Data Index: 294759 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.4773. Min Act: -0.1700

Data Index: 57829 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.5243. Min Act: -0.1700

Data Index: 424033 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.5087. Min Act: -0.1700

Data Index: 1616840 (Python Code)

Max Activating Token Index: 64

Text #12

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.4930. Min Act: -0.1700

Data Index: 1441104 (Python Code)

Max Activating Token Index: 273

Text #13

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.4773. Min Act: -0.1700

Data Index: 408168 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.4460. Min Act: -0.1700

Data Index: 899914 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.4773. Min Act: -0.1700

Data Index: 1539260 (Python Code)

Max Activating Token Index: 56

Text #16

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.4773. Min Act: -0.1700

Data Index: 1581809 (Python Code)

Max Activating Token Index: 57

Text #17

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.4617. Min Act: -0.1700

Data Index: 404558 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.4303. Min Act: -0.1700

Data Index: 418433 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 3.8530. Min Range: -3.8530

Max Act: 3.4303. Min Act: -0.1700

Data Index: 1652637 (Python Code)

Max Activating Token Index: 63