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

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

Neuron 1168 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2378. Min Range: -1.2378

Max Act: 1.2378. Min Act: -0.0000

Data Index: 507926 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 1.2378. Min Range: -1.2378

Max Act: 1.1343. Min Act: -0.0000

Data Index: 392928 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 1.2378. Min Range: -1.2378

Max Act: 0.7947. Min Act: -0.0000

Data Index: 657584 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 1.2378. Min Range: -1.2378

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1316290 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 1.2378. Min Range: -1.2378

Max Act: 0.7106. Min Act: -0.0000

Data Index: 795204 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 1.2378. Min Range: -1.2378

Max Act: 0.7463. Min Act: -0.0000

Data Index: 153560 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 1.2378. Min Range: -1.2378

Max Act: 0.6125. Min Act: -0.0000

Data Index: 380569 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 1.2378. Min Range: -1.2378

Max Act: 0.6665. Min Act: -0.0000

Data Index: 1106080 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 1.2378. Min Range: -1.2378

Max Act: 0.6166. Min Act: -0.0000

Data Index: 1341369 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 1.2378. Min Range: -1.2378

Max Act: 0.6905. Min Act: -0.0000

Data Index: 1293225 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 1.2378. Min Range: -1.2378

Max Act: 0.5130. Min Act: -0.0000

Data Index: 452071 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 1.2378. Min Range: -1.2378

Max Act: 0.6525. Min Act: -0.0000

Data Index: 922904 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 1.2378. Min Range: -1.2378

Max Act: 0.6159. Min Act: -0.0000

Data Index: 721550 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 1.2378. Min Range: -1.2378

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1345591 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 1.2378. Min Range: -1.2378

Max Act: 0.6110. Min Act: -0.0000

Data Index: 810234 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 1.2378. Min Range: -1.2378

Max Act: 0.4202. Min Act: -0.0000

Data Index: 261748 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 1.2378. Min Range: -1.2378

Max Act: 0.4427. Min Act: -0.0000

Data Index: 897883 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 1.2378. Min Range: -1.2378

Max Act: 0.5422. Min Act: -0.0000

Data Index: 670231 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 1.2378. Min Range: -1.2378

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1015413 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 1.2378. Min Range: -1.2378

Max Act: 0.5839. Min Act: -0.0000

Data Index: 76684 (C4 (Web Text))

Max Activating Token Index: 404