Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2599 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1479107 (The Pile)

Max Activating Token Index: 318

Text #1

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1396049 (The Pile)

Max Activating Token Index: 368

Text #2

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1995128 (The Pile)

Max Activating Token Index: 462

Text #3

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.4249. Min Act: -0.0000

Data Index: 1548959 (The Pile)

Max Activating Token Index: 991

Text #4

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1861891 (The Pile)

Max Activating Token Index: 630

Text #5

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.4029. Min Act: 0.0000

Data Index: 688537 (The Pile)

Max Activating Token Index: 238

Text #6

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.4070. Min Act: -0.0000

Data Index: 679571 (The Pile)

Max Activating Token Index: 369

Text #7

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3897. Min Act: -0.0000

Data Index: 1515873 (The Pile)

Max Activating Token Index: 526

Text #8

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.4143. Min Act: -0.0000

Data Index: 357590 (The Pile)

Max Activating Token Index: 199

Text #9

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.4090. Min Act: -0.0000

Data Index: 632513 (The Pile)

Max Activating Token Index: 109

Text #10

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1301249 (The Pile)

Max Activating Token Index: 949

Text #11

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3982. Min Act: -0.0000

Data Index: 103137 (The Pile)

Max Activating Token Index: 249

Text #12

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3708. Min Act: -0.0000

Data Index: 189301 (The Pile)

Max Activating Token Index: 902

Text #13

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3754. Min Act: -0.0000

Data Index: 477211 (The Pile)

Max Activating Token Index: 175

Text #14

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3623. Min Act: 0.0001

Data Index: 258066 (The Pile)

Max Activating Token Index: 962

Text #15

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1816681 (The Pile)

Max Activating Token Index: 85

Text #16

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3620. Min Act: -0.0000

Data Index: 30460 (The Pile)

Max Activating Token Index: 58

Text #17

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3730. Min Act: 0.0000

Data Index: 1001347 (The Pile)

Max Activating Token Index: 755

Text #18

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1368920 (The Pile)

Max Activating Token Index: 950

Text #19

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3769. Min Act: -0.0000

Data Index: 1526056 (The Pile)

Max Activating Token Index: 961