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

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

Neuron 511 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: 1.4402. Min Range: -1.4402

Max Act: 1.4402. Min Act: -0.0000

Data Index: 748390 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.1769. Min Act: -0.0000

Data Index: 980573 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.1297. Min Act: -0.0000

Data Index: 866047 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.0898. Min Act: -0.0000

Data Index: 969757 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.1104. Min Act: -0.0001

Data Index: 450357 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.1134. Min Act: -0.0000

Data Index: 460949 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.1086. Min Act: -0.0000

Data Index: 458363 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.0679. Min Act: -0.0000

Data Index: 5093 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.0968. Min Act: -0.0000

Data Index: 1578700 (Python Code)

Max Activating Token Index: 805

Text #9

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.1069. Min Act: -0.0000

Data Index: 214803 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.0891. Min Act: -0.0000

Data Index: 691879 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.0548. Min Act: -0.0000

Data Index: 139575 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.0824. Min Act: -0.0000

Data Index: 296991 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.0212. Min Act: -0.0000

Data Index: 1635929 (Python Code)

Max Activating Token Index: 96

Text #14

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.1213. Min Act: -0.0000

Data Index: 1344145 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.1549. Min Act: -0.0000

Data Index: 1648989 (Python Code)

Max Activating Token Index: 101

Text #16

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.1093. Min Act: -0.0000

Data Index: 1467782 (Python Code)

Max Activating Token Index: 85

Text #17

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.0712. Min Act: -0.0000

Data Index: 382436 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.0635. Min Act: -0.0000

Data Index: 202323 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.0676. Min Act: -0.0000

Data Index: 438643 (C4 (Web Text))

Max Activating Token Index: 935