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

Dataset: The Pile

Neuron 4074 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: 1.8264. Min Range: -1.8264

Max Act: 1.8264. Min Act: -0.0000

Data Index: 1393643 (The Pile)

Max Activating Token Index: 711

Text #1

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.5615. Min Act: -0.0000

Data Index: 1270321 (The Pile)

Max Activating Token Index: 349

Text #2

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.7091. Min Act: -0.0000

Data Index: 1293759 (The Pile)

Max Activating Token Index: 747

Text #3

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.5858. Min Act: -0.0000

Data Index: 1092074 (The Pile)

Max Activating Token Index: 763

Text #4

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.5412. Min Act: -0.0000

Data Index: 943381 (The Pile)

Max Activating Token Index: 516

Text #5

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.4681. Min Act: -0.0000

Data Index: 429556 (The Pile)

Max Activating Token Index: 887

Text #6

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.3920. Min Act: -0.0000

Data Index: 318606 (The Pile)

Max Activating Token Index: 230

Text #7

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.3851. Min Act: -0.0000

Data Index: 1990430 (The Pile)

Max Activating Token Index: 380

Text #8

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.4259. Min Act: -0.0000

Data Index: 1765476 (The Pile)

Max Activating Token Index: 732

Text #9

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.3863. Min Act: -0.0000

Data Index: 1041281 (The Pile)

Max Activating Token Index: 335

Text #10

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.3971. Min Act: -0.0000

Data Index: 1070673 (The Pile)

Max Activating Token Index: 938

Text #11

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.3736. Min Act: -0.0000

Data Index: 1546541 (The Pile)

Max Activating Token Index: 616

Text #12

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.2928. Min Act: -0.0000

Data Index: 425134 (The Pile)

Max Activating Token Index: 792

Text #13

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.3724. Min Act: -0.0000

Data Index: 1171018 (The Pile)

Max Activating Token Index: 425

Text #14

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.4574. Min Act: -0.0000

Data Index: 1689430 (The Pile)

Max Activating Token Index: 393

Text #15

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.2432. Min Act: -0.0000

Data Index: 1141720 (The Pile)

Max Activating Token Index: 638

Text #16

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.5343. Min Act: -0.0000

Data Index: 987647 (The Pile)

Max Activating Token Index: 727

Text #17

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.3793. Min Act: -0.0000

Data Index: 1637220 (The Pile)

Max Activating Token Index: 897

Text #18

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.3091. Min Act: -0.0000

Data Index: 396375 (The Pile)

Max Activating Token Index: 346

Text #19

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.2257. Min Act: -0.0000

Data Index: 1497959 (The Pile)

Max Activating Token Index: 27