Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3282 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3841. Min Act: -0.0001

Data Index: 1293764 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.2974. Min Act: -0.0001

Data Index: 1005070 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3793. Min Act: -0.0001

Data Index: 1042717 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.2606. Min Act: -0.0000

Data Index: 417553 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.2552. Min Act: -0.0001

Data Index: 257633 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3970. Min Act: -0.0001

Data Index: 859949 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.2599. Min Act: -0.0001

Data Index: 102038 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3865. Min Act: -0.0001

Data Index: 294474 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.2745. Min Act: -0.0000

Data Index: 1116494 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.2885. Min Act: -0.0000

Data Index: 886229 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3213. Min Act: -0.0001

Data Index: 92251 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.2744. Min Act: -0.0001

Data Index: 545123 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3296. Min Act: -0.0001

Data Index: 701976 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.2711. Min Act: -0.0000

Data Index: 206565 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.2710. Min Act: -0.0000

Data Index: 307992 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.2173. Min Act: -0.0001

Data Index: 989350 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.2150. Min Act: -0.0001

Data Index: 224401 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.2504. Min Act: -0.0001

Data Index: 774913 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.1928. Min Act: -0.0001

Data Index: 1171758 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.1947. Min Act: -0.0001

Data Index: 651428 (C4 (Web Text))

Max Activating Token Index: 678