Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4455 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.3594. Min Act: -0.0000

Data Index: 31490 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.3122. Min Act: -0.0001

Data Index: 628905 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.3066. Min Act: -0.0001

Data Index: 292606 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.3048. Min Act: -0.0001

Data Index: 27024 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.2788. Min Act: -0.0001

Data Index: 29960 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.2806. Min Act: -0.0001

Data Index: 857468 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.2518. Min Act: -0.0001

Data Index: 1325133 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.2543. Min Act: -0.0000

Data Index: 395691 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.2933. Min Act: -0.0000

Data Index: 1085036 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.2772. Min Act: -0.0001

Data Index: 768014 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.2937. Min Act: -0.0001

Data Index: 1008287 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.2728. Min Act: -0.0001

Data Index: 1146896 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.2861. Min Act: -0.0000

Data Index: 285211 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.3272. Min Act: -0.0000

Data Index: 780538 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.2597. Min Act: -0.0001

Data Index: 588913 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.2634. Min Act: -0.0001

Data Index: 450227 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.2345. Min Act: -0.0001

Data Index: 765980 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.2693. Min Act: -0.0000

Data Index: 49345 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.2618. Min Act: -0.0000

Data Index: 746251 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.3594. Min Range: -0.3594

Max Act: 0.2442. Min Act: -0.0001

Data Index: 240927 (C4 (Web Text))

Max Activating Token Index: 185