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

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

Neuron 1660 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.5653. Min Act: -0.1700

Data Index: 663021 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.5184. Min Act: -0.1700

Data Index: 1179680 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.4557. Min Act: -0.1700

Data Index: 412381 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.5027. Min Act: -0.1700

Data Index: 683333 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.5027. Min Act: -0.1700

Data Index: 543907 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.4400. Min Act: -0.1700

Data Index: 1038652 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.4713. Min Act: -0.1700

Data Index: 829151 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.4870. Min Act: -0.1700

Data Index: 781982 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.4243. Min Act: -0.1700

Data Index: 379562 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.4400. Min Act: -0.1700

Data Index: 1240636 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.4086. Min Act: -0.1700

Data Index: 1070628 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.4400. Min Act: -0.1700

Data Index: 753904 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.3616. Min Act: -0.1700

Data Index: 619138 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.3616. Min Act: -0.1700

Data Index: 599487 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.3459. Min Act: -0.1700

Data Index: 373405 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.3459. Min Act: -0.1700

Data Index: 787737 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.3616. Min Act: -0.1700

Data Index: 355225 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.3302. Min Act: -0.1700

Data Index: 1069101 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.3302. Min Act: -0.1700

Data Index: 279064 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 3.5653. Min Range: -3.5653

Max Act: 3.3302. Min Act: -0.1700

Data Index: 1055515 (C4 (Web Text))

Max Activating Token Index: 617