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

Dataset: The Pile

Neuron 1416 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.9710. Min Act: -0.0000

Data Index: 590213 (The Pile)

Max Activating Token Index: 174

Text #1

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8990. Min Act: -0.0000

Data Index: 1652470 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 1.0030. Min Range: -1.0030

Max Act: 1.0030. Min Act: -0.0000

Data Index: 1329785 (The Pile)

Max Activating Token Index: 399

Text #3

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7715. Min Act: -0.0000

Data Index: 1840262 (The Pile)

Max Activating Token Index: 542

Text #4

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6997. Min Act: -0.0000

Data Index: 1545834 (The Pile)

Max Activating Token Index: 1011

Text #5

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7041. Min Act: -0.0000

Data Index: 997992 (The Pile)

Max Activating Token Index: 70

Text #6

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1963219 (The Pile)

Max Activating Token Index: 370

Text #7

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7824. Min Act: -0.0000

Data Index: 869876 (The Pile)

Max Activating Token Index: 796

Text #8

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7547. Min Act: -0.0000

Data Index: 944018 (The Pile)

Max Activating Token Index: 691

Text #9

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8195. Min Act: -0.0000

Data Index: 297993 (The Pile)

Max Activating Token Index: 84

Text #10

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1301536 (The Pile)

Max Activating Token Index: 101

Text #11

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7069. Min Act: -0.0000

Data Index: 91736 (The Pile)

Max Activating Token Index: 419

Text #12

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6640. Min Act: -0.0000

Data Index: 354705 (The Pile)

Max Activating Token Index: 268

Text #13

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6456. Min Act: -0.0000

Data Index: 953268 (The Pile)

Max Activating Token Index: 502

Text #14

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6365. Min Act: -0.0000

Data Index: 1374330 (The Pile)

Max Activating Token Index: 758

Text #15

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6846. Min Act: -0.0000

Data Index: 702137 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6787. Min Act: -0.0000

Data Index: 272330 (The Pile)

Max Activating Token Index: 511

Text #17

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1669773 (The Pile)

Max Activating Token Index: 345

Text #18

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6136. Min Act: -0.0000

Data Index: 83709 (The Pile)

Max Activating Token Index: 152

Text #19

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6323. Min Act: -0.0000

Data Index: 543954 (The Pile)

Max Activating Token Index: 104