Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 10 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1941642 (The Pile)

Max Activating Token Index: 652

Text #1

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.7024. Min Act: -0.0000

Data Index: 1129514 (The Pile)

Max Activating Token Index: 23

Text #2

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1494671 (The Pile)

Max Activating Token Index: 133

Text #3

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.5868. Min Act: -0.0000

Data Index: 1924103 (The Pile)

Max Activating Token Index: 253

Text #4

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1615804 (The Pile)

Max Activating Token Index: 575

Text #5

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1840732 (The Pile)

Max Activating Token Index: 232

Text #6

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.5341. Min Act: -0.0001

Data Index: 252388 (The Pile)

Max Activating Token Index: 941

Text #7

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.5403. Min Act: -0.0000

Data Index: 178968 (The Pile)

Max Activating Token Index: 201

Text #8

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.5195. Min Act: -0.0000

Data Index: 352289 (The Pile)

Max Activating Token Index: 741

Text #9

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.4961. Min Act: -0.0000

Data Index: 500306 (The Pile)

Max Activating Token Index: 528

Text #10

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1439912 (The Pile)

Max Activating Token Index: 586

Text #11

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.4711. Min Act: -0.0000

Data Index: 627020 (The Pile)

Max Activating Token Index: 907

Text #12

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1948614 (The Pile)

Max Activating Token Index: 969

Text #13

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.4380. Min Act: -0.0001

Data Index: 1545343 (The Pile)

Max Activating Token Index: 133

Text #14

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.4992. Min Act: -0.0001

Data Index: 928740 (The Pile)

Max Activating Token Index: 1009

Text #15

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.4251. Min Act: -0.0000

Data Index: 630211 (The Pile)

Max Activating Token Index: 878

Text #16

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1151874 (The Pile)

Max Activating Token Index: 399

Text #17

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.4258. Min Act: -0.0000

Data Index: 923403 (The Pile)

Max Activating Token Index: 413

Text #18

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.4236. Min Act: 0.0000

Data Index: 433649 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1256026 (The Pile)

Max Activating Token Index: 976