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

Dataset: The Pile

Neuron 390 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3945. Min Act: -0.0000

Data Index: 1669160 (The Pile)

Max Activating Token Index: 76

Text #1

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1649462 (The Pile)

Max Activating Token Index: 67

Text #2

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3544. Min Act: -0.0000

Data Index: 111093 (The Pile)

Max Activating Token Index: 682

Text #3

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3721. Min Act: -0.0000

Data Index: 636870 (The Pile)

Max Activating Token Index: 557

Text #4

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3618. Min Act: -0.0000

Data Index: 605681 (The Pile)

Max Activating Token Index: 672

Text #5

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3466. Min Act: -0.0000

Data Index: 211883 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1238762 (The Pile)

Max Activating Token Index: 502

Text #7

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3405. Min Act: -0.0000

Data Index: 811100 (The Pile)

Max Activating Token Index: 900

Text #8

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3711. Min Act: -0.0000

Data Index: 907684 (The Pile)

Max Activating Token Index: 309

Text #9

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1894550 (The Pile)

Max Activating Token Index: 679

Text #10

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1343081 (The Pile)

Max Activating Token Index: 713

Text #11

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1008267 (The Pile)

Max Activating Token Index: 849

Text #12

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3558. Min Act: -0.0000

Data Index: 1393552 (The Pile)

Max Activating Token Index: 342

Text #13

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3569. Min Act: -0.0000

Data Index: 1130687 (The Pile)

Max Activating Token Index: 675

Text #14

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1398083 (The Pile)

Max Activating Token Index: 409

Text #15

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3127. Min Act: -0.0000

Data Index: 306173 (The Pile)

Max Activating Token Index: 547

Text #16

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3428. Min Act: -0.0000

Data Index: 1945700 (The Pile)

Max Activating Token Index: 200

Text #17

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1247706 (The Pile)

Max Activating Token Index: 476

Text #18

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1236752 (The Pile)

Max Activating Token Index: 231

Text #19

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3401. Min Act: -0.0000

Data Index: 261461 (The Pile)

Max Activating Token Index: 682