Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2741 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.9256. Min Act: -0.0001

Data Index: 1036991 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.9465. Min Act: -0.0001

Data Index: 778985 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.8799. Min Act: -0.0001

Data Index: 980074 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.7402. Min Act: -0.0001

Data Index: 1356681 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.7446. Min Act: -0.0001

Data Index: 373593 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.7304. Min Act: -0.0001

Data Index: 1067963 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.7192. Min Act: -0.0001

Data Index: 710481 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.6986. Min Act: -0.0001

Data Index: 760614 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.6707. Min Act: -0.0001

Data Index: 11872 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.7579. Min Act: -0.0001

Data Index: 136068 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.7068. Min Act: -0.0001

Data Index: 791469 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.7230. Min Act: -0.0001

Data Index: 870600 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.7019. Min Act: -0.0001

Data Index: 878659 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.7166. Min Act: -0.0001

Data Index: 1342517 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.6475. Min Act: -0.0001

Data Index: 1049590 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.6765. Min Act: -0.0001

Data Index: 77855 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.6785. Min Act: -0.0001

Data Index: 350345 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.6344. Min Act: -0.0001

Data Index: 33050 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.6734. Min Act: -0.0001

Data Index: 1285456 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.7300. Min Act: -0.0001

Data Index: 949995 (C4 (Web Text))

Max Activating Token Index: 620