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

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

Neuron 237 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: 3.0937. Min Range: -3.0937

Max Act: 3.0937. Min Act: -0.1700

Data Index: 104461 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 3.0937. Min Range: -3.0937

Max Act: 3.0780. Min Act: -0.1700

Data Index: 850001 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 3.0937. Min Range: -3.0937

Max Act: 3.0464. Min Act: -0.1700

Data Index: 313426 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 3.0937. Min Range: -3.0937

Max Act: 3.0306. Min Act: -0.1700

Data Index: 1633580 (Python Code)

Max Activating Token Index: 114

Text #4

Max Range: 3.0937. Min Range: -3.0937

Max Act: 3.0306. Min Act: -0.1700

Data Index: 1252279 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 3.0937. Min Range: -3.0937

Max Act: 3.0464. Min Act: -0.1700

Data Index: 766435 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 3.0937. Min Range: -3.0937

Max Act: 3.0306. Min Act: -0.1700

Data Index: 426753 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 3.0937. Min Range: -3.0937

Max Act: 3.0148. Min Act: -0.1700

Data Index: 812737 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 3.0937. Min Range: -3.0937

Max Act: 2.9990. Min Act: -0.1700

Data Index: 377018 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 3.0937. Min Range: -3.0937

Max Act: 2.9990. Min Act: -0.1700

Data Index: 355989 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 3.0937. Min Range: -3.0937

Max Act: 2.9990. Min Act: -0.1700

Data Index: 1067107 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 3.0937. Min Range: -3.0937

Max Act: 2.9515. Min Act: -0.1700

Data Index: 1168507 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 3.0937. Min Range: -3.0937

Max Act: 2.9515. Min Act: -0.1700

Data Index: 611611 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 3.0937. Min Range: -3.0937

Max Act: 2.9515. Min Act: -0.1700

Data Index: 300450 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 3.0937. Min Range: -3.0937

Max Act: 2.9515. Min Act: -0.1700

Data Index: 127624 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 3.0937. Min Range: -3.0937

Max Act: 2.9357. Min Act: -0.1700

Data Index: 476117 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 3.0937. Min Range: -3.0937

Max Act: 2.9198. Min Act: -0.1700

Data Index: 1198168 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 3.0937. Min Range: -3.0937

Max Act: 2.9198. Min Act: -0.1700

Data Index: 1049254 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 3.0937. Min Range: -3.0937

Max Act: 2.9040. Min Act: -0.1700

Data Index: 141447 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 3.0937. Min Range: -3.0937

Max Act: 2.9198. Min Act: -0.1700

Data Index: 535183 (C4 (Web Text))

Max Activating Token Index: 961