Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 644 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4641. Min Act: -0.0000

Data Index: 267546 (The Pile)

Max Activating Token Index: 613

Text #1

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4746. Min Act: -0.0000

Data Index: 430281 (The Pile)

Max Activating Token Index: 139

Text #2

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4279. Min Act: -0.0000

Data Index: 1327718 (The Pile)

Max Activating Token Index: 290

Text #3

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1375968 (The Pile)

Max Activating Token Index: 71

Text #4

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4006. Min Act: -0.0000

Data Index: 1963896 (The Pile)

Max Activating Token Index: 547

Text #5

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4393. Min Act: -0.0000

Data Index: 91710 (The Pile)

Max Activating Token Index: 526

Text #6

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4216. Min Act: -0.0000

Data Index: 301727 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4171. Min Act: 0.0000

Data Index: 1413040 (The Pile)

Max Activating Token Index: 649

Text #8

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3974. Min Act: 0.0000

Data Index: 422439 (The Pile)

Max Activating Token Index: 66

Text #9

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3821. Min Act: -0.0000

Data Index: 1126147 (The Pile)

Max Activating Token Index: 820

Text #10

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3513. Min Act: -0.0000

Data Index: 1949408 (The Pile)

Max Activating Token Index: 166

Text #11

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3621. Min Act: -0.0000

Data Index: 394281 (The Pile)

Max Activating Token Index: 726

Text #12

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3737. Min Act: -0.0000

Data Index: 872227 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3533. Min Act: -0.0000

Data Index: 1474280 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3737. Min Act: -0.0000

Data Index: 1576200 (The Pile)

Max Activating Token Index: 71

Text #15

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3730. Min Act: -0.0000

Data Index: 333890 (The Pile)

Max Activating Token Index: 15

Text #16

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1205774 (The Pile)

Max Activating Token Index: 526

Text #17

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3444. Min Act: -0.0000

Data Index: 486623 (The Pile)

Max Activating Token Index: 253

Text #18

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3428. Min Act: -0.0000

Data Index: 815048 (The Pile)

Max Activating Token Index: 74

Text #19

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3250. Min Act: -0.0000

Data Index: 451210 (The Pile)

Max Activating Token Index: 468