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

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

Neuron 2463 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8829. Min Act: -0.0001

Data Index: 382942 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8405. Min Act: -0.0001

Data Index: 692042 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8533. Min Act: -0.0001

Data Index: 1230121 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8241. Min Act: -0.0001

Data Index: 859967 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8204. Min Act: -0.0001

Data Index: 470965 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8174. Min Act: -0.0001

Data Index: 488713 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7763. Min Act: -0.0001

Data Index: 470015 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7964. Min Act: -0.0001

Data Index: 1058391 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7718. Min Act: -0.0001

Data Index: 504051 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7881. Min Act: -0.0001

Data Index: 239137 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7237. Min Act: -0.0001

Data Index: 651837 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7833. Min Act: -0.0001

Data Index: 794891 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7782. Min Act: -0.0001

Data Index: 674698 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7434. Min Act: -0.0001

Data Index: 915936 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7276. Min Act: -0.0001

Data Index: 1171545 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7496. Min Act: -0.0001

Data Index: 739621 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6740. Min Act: -0.0001

Data Index: 367579 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6708. Min Act: -0.0001

Data Index: 26585 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6945. Min Act: -0.0001

Data Index: 531914 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7051. Min Act: -0.0001

Data Index: 114149 (C4 (Web Text))

Max Activating Token Index: 274