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

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

Neuron 39 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: 3.9859. Min Range: -3.9859

Max Act: 3.9859. Min Act: -0.1700

Data Index: 1193262 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 3.9859. Min Range: -3.9859

Max Act: 3.7670. Min Act: -0.1700

Data Index: 777671 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 3.9859. Min Range: -3.9859

Max Act: 3.7983. Min Act: -0.1700

Data Index: 77362 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 3.9859. Min Range: -3.9859

Max Act: 3.7357. Min Act: -0.1700

Data Index: 695233 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 3.9859. Min Range: -3.9859

Max Act: 3.7357. Min Act: -0.1700

Data Index: 421666 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 3.9859. Min Range: -3.9859

Max Act: 3.7044. Min Act: -0.1700

Data Index: 109362 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 3.9859. Min Range: -3.9859

Max Act: 3.6731. Min Act: -0.1700

Data Index: 1214363 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 3.9859. Min Range: -3.9859

Max Act: 3.7044. Min Act: -0.1700

Data Index: 116349 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 3.9859. Min Range: -3.9859

Max Act: 3.6731. Min Act: -0.1700

Data Index: 1247572 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 3.9859. Min Range: -3.9859

Max Act: 3.6731. Min Act: -0.1700

Data Index: 555912 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 3.9859. Min Range: -3.9859

Max Act: 3.7044. Min Act: -0.1700

Data Index: 1310942 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 3.9859. Min Range: -3.9859

Max Act: 3.7044. Min Act: -0.1700

Data Index: 662637 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 3.9859. Min Range: -3.9859

Max Act: 3.7044. Min Act: -0.1700

Data Index: 294220 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 3.9859. Min Range: -3.9859

Max Act: 3.6731. Min Act: -0.1700

Data Index: 346216 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 3.9859. Min Range: -3.9859

Max Act: 3.7044. Min Act: -0.1700

Data Index: 664981 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 3.9859. Min Range: -3.9859

Max Act: 3.6731. Min Act: -0.1700

Data Index: 172516 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 3.9859. Min Range: -3.9859

Max Act: 3.6731. Min Act: -0.1700

Data Index: 731278 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 3.9859. Min Range: -3.9859

Max Act: 3.6731. Min Act: -0.1700

Data Index: 239359 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 3.9859. Min Range: -3.9859

Max Act: 3.6418. Min Act: -0.1700

Data Index: 284569 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 3.9859. Min Range: -3.9859

Max Act: 3.6731. Min Act: -0.1700

Data Index: 838274 (C4 (Web Text))

Max Activating Token Index: 623