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

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

Neuron 4055 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1441593 (Python Code)

Max Activating Token Index: 125

Text #1

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1534631 (Python Code)

Max Activating Token Index: 410

Text #2

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1428753 (Python Code)

Max Activating Token Index: 711

Text #3

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5687. Min Act: -0.0000

Data Index: 1500706 (Python Code)

Max Activating Token Index: 114

Text #4

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1362325 (Python Code)

Max Activating Token Index: 208

Text #5

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1560319 (Python Code)

Max Activating Token Index: 147

Text #6

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5482. Min Act: -0.0000

Data Index: 1389462 (Python Code)

Max Activating Token Index: 559

Text #7

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5069. Min Act: -0.0000

Data Index: 1580493 (Python Code)

Max Activating Token Index: 828

Text #8

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1415646 (Python Code)

Max Activating Token Index: 385

Text #9

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5022. Min Act: -0.0000

Data Index: 1442026 (Python Code)

Max Activating Token Index: 413

Text #10

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5281. Min Act: -0.0000

Data Index: 1384858 (Python Code)

Max Activating Token Index: 727

Text #11

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5289. Min Act: -0.0000

Data Index: 1467039 (Python Code)

Max Activating Token Index: 180

Text #12

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5048. Min Act: -0.0000

Data Index: 1367825 (Python Code)

Max Activating Token Index: 529

Text #13

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1531264 (Python Code)

Max Activating Token Index: 642

Text #14

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.4635. Min Act: -0.0000

Data Index: 1625126 (Python Code)

Max Activating Token Index: 501

Text #15

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.4711. Min Act: -0.0000

Data Index: 1380067 (Python Code)

Max Activating Token Index: 74

Text #16

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1625743 (Python Code)

Max Activating Token Index: 527

Text #17

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1494668 (Python Code)

Max Activating Token Index: 624

Text #18

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.4016. Min Act: -0.0000

Data Index: 1549837 (Python Code)

Max Activating Token Index: 1019

Text #19

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.4749. Min Act: -0.0000

Data Index: 1512621 (Python Code)

Max Activating Token Index: 1006