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

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

Neuron 1572 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: 3.8299. Min Range: -3.8299

Max Act: 3.8299. Min Act: -0.1700

Data Index: 917154 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.7673. Min Act: -0.1700

Data Index: 1266674 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.7047. Min Act: -0.1700

Data Index: 777030 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.6734. Min Act: -0.1700

Data Index: 3447 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.6421. Min Act: -0.1700

Data Index: 1129477 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.6108. Min Act: -0.1700

Data Index: 1043707 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.6421. Min Act: -0.1700

Data Index: 324980 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5795. Min Act: -0.1700

Data Index: 483256 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5795. Min Act: -0.1700

Data Index: 973958 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5795. Min Act: -0.1700

Data Index: 333519 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5795. Min Act: -0.1700

Data Index: 171038 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5795. Min Act: -0.1700

Data Index: 405986 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5795. Min Act: -0.1700

Data Index: 736322 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5795. Min Act: -0.1700

Data Index: 636244 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5482. Min Act: -0.1700

Data Index: 9250 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.6421. Min Act: -0.1700

Data Index: 366083 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.6108. Min Act: -0.1700

Data Index: 414478 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5795. Min Act: -0.1700

Data Index: 559800 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5795. Min Act: -0.1700

Data Index: 907530 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5482. Min Act: -0.1700

Data Index: 934861 (C4 (Web Text))

Max Activating Token Index: 88