Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 267 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1174704 (The Pile)

Max Activating Token Index: 343

Text #1

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1767008 (The Pile)

Max Activating Token Index: 744

Text #2

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.5276. Min Act: -0.0000

Data Index: 263538 (The Pile)

Max Activating Token Index: 282

Text #3

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1541527 (The Pile)

Max Activating Token Index: 647

Text #4

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1303386 (The Pile)

Max Activating Token Index: 218

Text #5

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4551. Min Act: -0.0000

Data Index: 1879453 (The Pile)

Max Activating Token Index: 13

Text #6

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4516. Min Act: -0.0000

Data Index: 283024 (The Pile)

Max Activating Token Index: 543

Text #7

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4215. Min Act: -0.0000

Data Index: 1562242 (The Pile)

Max Activating Token Index: 229

Text #8

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1651318 (The Pile)

Max Activating Token Index: 555

Text #9

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4031. Min Act: -0.0000

Data Index: 81125 (The Pile)

Max Activating Token Index: 876

Text #10

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4052. Min Act: -0.0000

Data Index: 282071 (The Pile)

Max Activating Token Index: 455

Text #11

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4316. Min Act: -0.0000

Data Index: 1288524 (The Pile)

Max Activating Token Index: 544

Text #12

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4108. Min Act: -0.0000

Data Index: 964950 (The Pile)

Max Activating Token Index: 900

Text #13

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4121. Min Act: -0.0000

Data Index: 284554 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.3965. Min Act: -0.0000

Data Index: 462254 (The Pile)

Max Activating Token Index: 290

Text #15

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1379570 (The Pile)

Max Activating Token Index: 795

Text #16

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4086. Min Act: -0.0000

Data Index: 929252 (The Pile)

Max Activating Token Index: 18

Text #17

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.3962. Min Act: -0.0000

Data Index: 736018 (The Pile)

Max Activating Token Index: 89

Text #18

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4058. Min Act: -0.0000

Data Index: 375650 (The Pile)

Max Activating Token Index: 79

Text #19

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1211854 (The Pile)

Max Activating Token Index: 285