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

Dataset: The Pile

Neuron 1551 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1757129 (The Pile)

Max Activating Token Index: 388

Text #1

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.5267. Min Act: -0.0000

Data Index: 387083 (The Pile)

Max Activating Token Index: 1001

Text #2

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4945. Min Act: -0.0000

Data Index: 1035318 (The Pile)

Max Activating Token Index: 123

Text #3

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.5051. Min Act: -0.0000

Data Index: 138316 (The Pile)

Max Activating Token Index: 282

Text #4

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1725341 (The Pile)

Max Activating Token Index: 745

Text #5

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4331. Min Act: -0.0000

Data Index: 388021 (The Pile)

Max Activating Token Index: 84

Text #6

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4601. Min Act: -0.0000

Data Index: 1439325 (The Pile)

Max Activating Token Index: 772

Text #7

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1437681 (The Pile)

Max Activating Token Index: 1021

Text #8

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4340. Min Act: -0.0000

Data Index: 364259 (The Pile)

Max Activating Token Index: 354

Text #9

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4076. Min Act: -0.0000

Data Index: 840864 (The Pile)

Max Activating Token Index: 462

Text #10

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1495696 (The Pile)

Max Activating Token Index: 815

Text #11

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4369. Min Act: -0.0000

Data Index: 267173 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4088. Min Act: -0.0000

Data Index: 1795008 (The Pile)

Max Activating Token Index: 753

Text #13

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4151. Min Act: -0.0000

Data Index: 968830 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4108. Min Act: -0.0000

Data Index: 375527 (The Pile)

Max Activating Token Index: 969

Text #15

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1694105 (The Pile)

Max Activating Token Index: 798

Text #16

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.3993. Min Act: -0.0000

Data Index: 897309 (The Pile)

Max Activating Token Index: 136

Text #17

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4478. Min Act: -0.0000

Data Index: 292552 (The Pile)

Max Activating Token Index: 147

Text #18

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.3900. Min Act: -0.0000

Data Index: 1463757 (The Pile)

Max Activating Token Index: 294

Text #19

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4233. Min Act: -0.0000

Data Index: 596318 (The Pile)

Max Activating Token Index: 751