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

Dataset: The Pile

Neuron 767 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.6389. Min Act: -0.0000

Data Index: 134651 (The Pile)

Max Activating Token Index: 864

Text #1

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.7230. Min Act: -0.0000

Data Index: 416216 (The Pile)

Max Activating Token Index: 767

Text #2

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.5380. Min Act: -0.0000

Data Index: 624578 (The Pile)

Max Activating Token Index: 48

Text #3

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.5453. Min Act: -0.0000

Data Index: 1774139 (The Pile)

Max Activating Token Index: 502

Text #4

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.6139. Min Act: -0.0000

Data Index: 148188 (The Pile)

Max Activating Token Index: 942

Text #5

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.4289. Min Act: -0.0000

Data Index: 1270808 (The Pile)

Max Activating Token Index: 718

Text #6

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.5119. Min Act: -0.0000

Data Index: 511652 (The Pile)

Max Activating Token Index: 537

Text #7

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.4919. Min Act: -0.0000

Data Index: 1077072 (The Pile)

Max Activating Token Index: 327

Text #8

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.5562. Min Act: -0.0000

Data Index: 1449599 (The Pile)

Max Activating Token Index: 984

Text #9

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.5587. Min Act: -0.0000

Data Index: 332445 (The Pile)

Max Activating Token Index: 280

Text #10

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.4705. Min Act: -0.0000

Data Index: 591960 (The Pile)

Max Activating Token Index: 31

Text #11

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.4493. Min Act: -0.0000

Data Index: 332086 (The Pile)

Max Activating Token Index: 202

Text #12

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.4245. Min Act: -0.0000

Data Index: 1316579 (The Pile)

Max Activating Token Index: 465

Text #13

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.4202. Min Act: -0.0000

Data Index: 1441885 (The Pile)

Max Activating Token Index: 627

Text #14

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.3311. Min Act: -0.0000

Data Index: 631950 (The Pile)

Max Activating Token Index: 698

Text #15

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.3912. Min Act: -0.0000

Data Index: 1221563 (The Pile)

Max Activating Token Index: 456

Text #16

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.3817. Min Act: -0.0000

Data Index: 933413 (The Pile)

Max Activating Token Index: 483

Text #17

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.2932. Min Act: -0.0000

Data Index: 283319 (The Pile)

Max Activating Token Index: 321

Text #18

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.3691. Min Act: -0.0000

Data Index: 397384 (The Pile)

Max Activating Token Index: 177

Text #19

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.4447. Min Act: -0.0000

Data Index: 825732 (The Pile)

Max Activating Token Index: 58