Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.5346. Min Act: -0.1700

Data Index: 95923 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.5502. Min Act: -0.1700

Data Index: 592979 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.5189. Min Act: -0.1700

Data Index: 528098 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.5189. Min Act: -0.1700

Data Index: 855664 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.5032. Min Act: -0.1700

Data Index: 123425 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.5032. Min Act: -0.1700

Data Index: 95464 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.5032. Min Act: -0.1700

Data Index: 894786 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.5032. Min Act: -0.1700

Data Index: 1108604 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.5032. Min Act: -0.1700

Data Index: 260623 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.4719. Min Act: -0.1700

Data Index: 747327 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.4249. Min Act: -0.1700

Data Index: 730824 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.4562. Min Act: -0.1700

Data Index: 31389 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.4562. Min Act: -0.1700

Data Index: 843591 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.4562. Min Act: -0.1700

Data Index: 433973 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.4405. Min Act: -0.1700

Data Index: 754471 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.4562. Min Act: -0.1700

Data Index: 90467 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.4562. Min Act: -0.1700

Data Index: 187751 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.4092. Min Act: -0.1700

Data Index: 274594 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.4249. Min Act: -0.1700

Data Index: 993663 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 3.5502. Min Range: -3.5502

Max Act: 3.4092. Min Act: -0.1700

Data Index: 115602 (C4 (Web Text))

Max Activating Token Index: 491