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

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

Neuron 678 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.8192. Min Act: -0.1700

Data Index: 450479 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.7879. Min Act: -0.1700

Data Index: 348659 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.7566. Min Act: -0.1700

Data Index: 945468 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.6627. Min Act: -0.1700

Data Index: 1329161 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.6627. Min Act: -0.1700

Data Index: 1241431 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.6314. Min Act: -0.1700

Data Index: 438315 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.6314. Min Act: -0.1700

Data Index: 433197 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.6314. Min Act: -0.1700

Data Index: 1227614 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.6627. Min Act: -0.1700

Data Index: 916981 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.5688. Min Act: -0.1700

Data Index: 979247 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.5688. Min Act: -0.1700

Data Index: 126559 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.5374. Min Act: -0.1700

Data Index: 165034 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.5688. Min Act: -0.1700

Data Index: 1006952 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.6001. Min Act: -0.1700

Data Index: 415584 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.5688. Min Act: -0.1700

Data Index: 757642 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.5374. Min Act: -0.1700

Data Index: 456724 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.5061. Min Act: -0.1700

Data Index: 293897 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.5374. Min Act: -0.1700

Data Index: 86901 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.5374. Min Act: -0.1700

Data Index: 609791 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 3.8192. Min Range: -3.8192

Max Act: 3.5374. Min Act: -0.1700

Data Index: 497116 (C4 (Web Text))

Max Activating Token Index: 397