Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1668 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.3409. Min Act: -0.1700

Data Index: 291353 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.3566. Min Act: -0.1700

Data Index: 1350695 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.3252. Min Act: -0.1700

Data Index: 22633 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.3252. Min Act: -0.1700

Data Index: 491226 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.3252. Min Act: -0.1700

Data Index: 500990 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.3095. Min Act: -0.1700

Data Index: 1365765 (Python Code)

Max Activating Token Index: 9

Text #6

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.3095. Min Act: -0.1700

Data Index: 500719 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.3095. Min Act: -0.1700

Data Index: 581798 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2781. Min Act: -0.1700

Data Index: 436453 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2938. Min Act: -0.1700

Data Index: 438627 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.3095. Min Act: -0.1700

Data Index: 328821 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2938. Min Act: -0.1700

Data Index: 1175389 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2938. Min Act: -0.1700

Data Index: 97301 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2781. Min Act: -0.1700

Data Index: 546625 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2938. Min Act: -0.1700

Data Index: 786080 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2938. Min Act: -0.1700

Data Index: 789462 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2781. Min Act: -0.1700

Data Index: 321017 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2624. Min Act: -0.1700

Data Index: 360497 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2781. Min Act: -0.1700

Data Index: 66 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2781. Min Act: -0.1700

Data Index: 41614 (C4 (Web Text))

Max Activating Token Index: 126