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

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

Neuron 1466 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: 4.1562. Min Range: -4.1562

Max Act: 4.1562. Min Act: -0.1700

Data Index: 585299 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 4.1562. Min Range: -4.1562

Max Act: 4.0624. Min Act: -0.1700

Data Index: 45602 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 4.1562. Min Range: -4.1562

Max Act: 4.0311. Min Act: -0.1700

Data Index: 179121 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 4.1562. Min Range: -4.1562

Max Act: 4.0311. Min Act: -0.1700

Data Index: 156211 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 4.1562. Min Range: -4.1562

Max Act: 3.9373. Min Act: -0.1700

Data Index: 249522 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 4.1562. Min Range: -4.1562

Max Act: 3.9373. Min Act: -0.1700

Data Index: 896431 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 4.1562. Min Range: -4.1562

Max Act: 3.9373. Min Act: -0.1700

Data Index: 295539 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 4.1562. Min Range: -4.1562

Max Act: 3.9060. Min Act: -0.1700

Data Index: 112757 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 4.1562. Min Range: -4.1562

Max Act: 3.9060. Min Act: -0.1700

Data Index: 398222 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 4.1562. Min Range: -4.1562

Max Act: 3.9060. Min Act: -0.1700

Data Index: 553862 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 4.1562. Min Range: -4.1562

Max Act: 3.8748. Min Act: -0.1700

Data Index: 1101842 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 4.1562. Min Range: -4.1562

Max Act: 3.8748. Min Act: -0.1700

Data Index: 613825 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 4.1562. Min Range: -4.1562

Max Act: 3.8435. Min Act: -0.1700

Data Index: 34722 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 4.1562. Min Range: -4.1562

Max Act: 3.8748. Min Act: -0.1700

Data Index: 654509 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 4.1562. Min Range: -4.1562

Max Act: 3.8748. Min Act: -0.1700

Data Index: 356535 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 4.1562. Min Range: -4.1562

Max Act: 3.8748. Min Act: -0.1700

Data Index: 430347 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 4.1562. Min Range: -4.1562

Max Act: 3.8748. Min Act: -0.1700

Data Index: 517788 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 4.1562. Min Range: -4.1562

Max Act: 3.8748. Min Act: -0.1700

Data Index: 787704 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 4.1562. Min Range: -4.1562

Max Act: 3.8122. Min Act: -0.1700

Data Index: 569467 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 4.1562. Min Range: -4.1562

Max Act: 3.8748. Min Act: -0.1700

Data Index: 298402 (C4 (Web Text))

Max Activating Token Index: 564