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

Dataset: The Pile

Neuron 3017 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: 5.5827. Min Range: -5.5827

Max Act: 5.2103. Min Act: -0.0000

Data Index: 886350 (The Pile)

Max Activating Token Index: 521

Text #1

Max Range: 5.5827. Min Range: -5.5827

Max Act: 4.5542. Min Act: -0.0000

Data Index: 1279982 (The Pile)

Max Activating Token Index: 818

Text #2

Max Range: 5.5827. Min Range: -5.5827

Max Act: 4.8823. Min Act: -0.0000

Data Index: 422367 (The Pile)

Max Activating Token Index: 839

Text #3

Max Range: 5.5827. Min Range: -5.5827

Max Act: 4.8812. Min Act: -0.0000

Data Index: 1995574 (The Pile)

Max Activating Token Index: 379

Text #4

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.5827. Min Act: -0.0000

Data Index: 1762350 (The Pile)

Max Activating Token Index: 531

Text #5

Max Range: 5.5827. Min Range: -5.5827

Max Act: 4.9929. Min Act: -0.0000

Data Index: 565350 (The Pile)

Max Activating Token Index: 695

Text #6

Max Range: 5.5827. Min Range: -5.5827

Max Act: 4.7946. Min Act: -0.0000

Data Index: 214029 (The Pile)

Max Activating Token Index: 601

Text #7

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.2942. Min Act: -0.0000

Data Index: 1752938 (The Pile)

Max Activating Token Index: 326

Text #8

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.1014. Min Act: -0.0000

Data Index: 1189784 (The Pile)

Max Activating Token Index: 301

Text #9

Max Range: 5.5827. Min Range: -5.5827

Max Act: 4.9428. Min Act: -0.0000

Data Index: 1104056 (The Pile)

Max Activating Token Index: 374

Text #10

Max Range: 5.5827. Min Range: -5.5827

Max Act: 4.5994. Min Act: -0.0000

Data Index: 44939 (The Pile)

Max Activating Token Index: 380

Text #11

Max Range: 5.5827. Min Range: -5.5827

Max Act: 4.4255. Min Act: -0.0000

Data Index: 844469 (The Pile)

Max Activating Token Index: 732

Text #12

Max Range: 5.5827. Min Range: -5.5827

Max Act: 4.5458. Min Act: -0.0000

Data Index: 1112732 (The Pile)

Max Activating Token Index: 854

Text #13

Max Range: 5.5827. Min Range: -5.5827

Max Act: 4.0262. Min Act: -0.0000

Data Index: 495694 (The Pile)

Max Activating Token Index: 649

Text #14

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.0259. Min Act: -0.0000

Data Index: 338198 (The Pile)

Max Activating Token Index: 618

Text #15

Max Range: 5.5827. Min Range: -5.5827

Max Act: 4.1564. Min Act: -0.0000

Data Index: 259844 (The Pile)

Max Activating Token Index: 789

Text #16

Max Range: 5.5827. Min Range: -5.5827

Max Act: 3.5573. Min Act: -0.0000

Data Index: 1678587 (The Pile)

Max Activating Token Index: 735

Text #17

Max Range: 5.5827. Min Range: -5.5827

Max Act: 4.6254. Min Act: -0.0000

Data Index: 387843 (The Pile)

Max Activating Token Index: 501

Text #18

Max Range: 5.5827. Min Range: -5.5827

Max Act: 4.4829. Min Act: -0.0000

Data Index: 694076 (The Pile)

Max Activating Token Index: 261

Text #19

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.2273. Min Act: -0.0000

Data Index: 393654 (The Pile)

Max Activating Token Index: 791