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

Dataset: The Pile

Neuron 2448 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1091977 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1949919 (The Pile)

Max Activating Token Index: 488

Text #2

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5942. Min Act: -0.0000

Data Index: 900037 (The Pile)

Max Activating Token Index: 722

Text #3

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1175689 (The Pile)

Max Activating Token Index: 693

Text #4

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5968. Min Act: -0.0000

Data Index: 967858 (The Pile)

Max Activating Token Index: 219

Text #5

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1982175 (The Pile)

Max Activating Token Index: 513

Text #6

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5437. Min Act: -0.0000

Data Index: 129821 (The Pile)

Max Activating Token Index: 286

Text #7

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1329199 (The Pile)

Max Activating Token Index: 154

Text #8

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5026. Min Act: -0.0000

Data Index: 417671 (The Pile)

Max Activating Token Index: 335

Text #9

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5490. Min Act: -0.0000

Data Index: 162487 (The Pile)

Max Activating Token Index: 179

Text #10

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5326. Min Act: -0.0000

Data Index: 135712 (The Pile)

Max Activating Token Index: 90

Text #11

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5631. Min Act: -0.0000

Data Index: 483095 (The Pile)

Max Activating Token Index: 508

Text #12

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5637. Min Act: -0.0000

Data Index: 1340873 (The Pile)

Max Activating Token Index: 248

Text #13

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5314. Min Act: -0.0000

Data Index: 949791 (The Pile)

Max Activating Token Index: 795

Text #14

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5230. Min Act: -0.0000

Data Index: 1432965 (The Pile)

Max Activating Token Index: 949

Text #15

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5057. Min Act: -0.0000

Data Index: 336551 (The Pile)

Max Activating Token Index: 755

Text #16

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1544020 (The Pile)

Max Activating Token Index: 244

Text #17

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5190. Min Act: -0.0000

Data Index: 352221 (The Pile)

Max Activating Token Index: 177

Text #18

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5257. Min Act: -0.0000

Data Index: 230792 (The Pile)

Max Activating Token Index: 812

Text #19

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1114350 (The Pile)

Max Activating Token Index: 566