Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1946 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.8462. Min Act: -0.1700

Data Index: 22865 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.8611. Min Act: -0.1700

Data Index: 223597 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.7418. Min Act: -0.1700

Data Index: 488517 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.7407. Min Act: -0.1700

Data Index: 706558 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.7353. Min Act: -0.1700

Data Index: 703502 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.7461. Min Act: -0.1700

Data Index: 599966 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.7100. Min Act: -0.1700

Data Index: 90709 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.6801. Min Act: -0.1700

Data Index: 56443 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.6743. Min Act: -0.1699

Data Index: 505609 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.6491. Min Act: -0.1700

Data Index: 590927 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.6278. Min Act: -0.1700

Data Index: 1235840 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.6453. Min Act: -0.1700

Data Index: 991489 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.6156. Min Act: -0.1700

Data Index: 1034983 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.5951. Min Act: -0.1700

Data Index: 657046 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.5833. Min Act: -0.1700

Data Index: 640439 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.6245. Min Act: -0.1700

Data Index: 966165 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.6019. Min Act: -0.1700

Data Index: 576585 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.5553. Min Act: -0.1700

Data Index: 748115 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.5867. Min Act: -0.1700

Data Index: 402567 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 3.8611. Min Range: -3.8611

Max Act: 3.5853. Min Act: -0.1700

Data Index: 1011767 (C4 (Web Text))

Max Activating Token Index: 624