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

Dataset: The Pile

Neuron 1201 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: 1.8462. Min Range: -1.8462

Max Act: 1.8295. Min Act: -0.0000

Data Index: 789630 (The Pile)

Max Activating Token Index: 713

Text #1

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.5947. Min Act: -0.0000

Data Index: 1101563 (The Pile)

Max Activating Token Index: 39

Text #2

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7816. Min Act: -0.0000

Data Index: 1808682 (The Pile)

Max Activating Token Index: 421

Text #3

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.8462. Min Act: -0.0000

Data Index: 553182 (The Pile)

Max Activating Token Index: 362

Text #4

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7259. Min Act: -0.0000

Data Index: 1777973 (The Pile)

Max Activating Token Index: 30

Text #5

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7975. Min Act: -0.0000

Data Index: 554706 (The Pile)

Max Activating Token Index: 817

Text #6

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.6951. Min Act: -0.0000

Data Index: 1302752 (The Pile)

Max Activating Token Index: 733

Text #7

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.6856. Min Act: -0.0000

Data Index: 80241 (The Pile)

Max Activating Token Index: 198

Text #8

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.7064. Min Act: -0.0000

Data Index: 1021115 (The Pile)

Max Activating Token Index: 613

Text #9

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.6034. Min Act: -0.0000

Data Index: 1144847 (The Pile)

Max Activating Token Index: 744

Text #10

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.5890. Min Act: -0.0000

Data Index: 1212880 (The Pile)

Max Activating Token Index: 251

Text #11

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.5340. Min Act: -0.0000

Data Index: 965152 (The Pile)

Max Activating Token Index: 199

Text #12

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.5486. Min Act: -0.0000

Data Index: 1664272 (The Pile)

Max Activating Token Index: 386

Text #13

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.6295. Min Act: -0.0000

Data Index: 1234318 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.4316. Min Act: -0.0000

Data Index: 1480439 (The Pile)

Max Activating Token Index: 942

Text #15

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.4322. Min Act: -0.0000

Data Index: 186335 (The Pile)

Max Activating Token Index: 601

Text #16

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.5428. Min Act: -0.0000

Data Index: 1629279 (The Pile)

Max Activating Token Index: 132

Text #17

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.5073. Min Act: -0.0000

Data Index: 1624189 (The Pile)

Max Activating Token Index: 397

Text #18

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.3660. Min Act: -0.0000

Data Index: 1754182 (The Pile)

Max Activating Token Index: 1000

Text #19

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.4890. Min Act: -0.0000

Data Index: 270014 (The Pile)

Max Activating Token Index: 526