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

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

Neuron 472 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: 3.2080. Min Range: -3.2080

Max Act: 3.2080. Min Act: -0.1700

Data Index: 218308 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 3.2080. Min Range: -3.2080

Max Act: 3.1954. Min Act: -0.1696

Data Index: 574910 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 3.2080. Min Range: -3.2080

Max Act: 3.1282. Min Act: -0.1700

Data Index: 92822 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 3.2080. Min Range: -3.2080

Max Act: 3.1293. Min Act: -0.1700

Data Index: 706335 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 3.2080. Min Range: -3.2080

Max Act: 3.0958. Min Act: -0.1700

Data Index: 664728 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 3.2080. Min Range: -3.2080

Max Act: 3.1111. Min Act: -0.1700

Data Index: 589466 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 3.2080. Min Range: -3.2080

Max Act: 3.0942. Min Act: -0.1700

Data Index: 942146 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 3.2080. Min Range: -3.2080

Max Act: 3.0880. Min Act: -0.1700

Data Index: 783666 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 3.2080. Min Range: -3.2080

Max Act: 3.0668. Min Act: -0.1700

Data Index: 1164496 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 3.2080. Min Range: -3.2080

Max Act: 3.0547. Min Act: -0.1700

Data Index: 767409 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 3.2080. Min Range: -3.2080

Max Act: 3.0824. Min Act: -0.1700

Data Index: 25216 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 3.2080. Min Range: -3.2080

Max Act: 3.0455. Min Act: -0.1700

Data Index: 886775 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 3.2080. Min Range: -3.2080

Max Act: 3.0723. Min Act: -0.1699

Data Index: 262537 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 3.2080. Min Range: -3.2080

Max Act: 3.0545. Min Act: -0.1700

Data Index: 1330463 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 3.2080. Min Range: -3.2080

Max Act: 3.0451. Min Act: -0.1700

Data Index: 1497887 (Python Code)

Max Activating Token Index: 1002

Text #15

Max Range: 3.2080. Min Range: -3.2080

Max Act: 3.0443. Min Act: -0.1700

Data Index: 695970 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 3.2080. Min Range: -3.2080

Max Act: 3.0445. Min Act: -0.1700

Data Index: 1239585 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 3.2080. Min Range: -3.2080

Max Act: 3.0301. Min Act: -0.1700

Data Index: 734952 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 3.2080. Min Range: -3.2080

Max Act: 3.0349. Min Act: -0.1700

Data Index: 460601 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 3.2080. Min Range: -3.2080

Max Act: 3.0417. Min Act: -0.1700

Data Index: 916914 (C4 (Web Text))

Max Activating Token Index: 457