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

Dataset: The Pile

Neuron 938 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0673. Min Range: -1.0673

Max Act: 1.0643. Min Act: -0.0000

Data Index: 481593 (The Pile)

Max Activating Token Index: 591

Text #1

Max Range: 1.0673. Min Range: -1.0673

Max Act: 1.0652. Min Act: -0.0000

Data Index: 106550 (The Pile)

Max Activating Token Index: 482

Text #2

Max Range: 1.0673. Min Range: -1.0673

Max Act: 1.0475. Min Act: -0.0000

Data Index: 1688904 (The Pile)

Max Activating Token Index: 331

Text #3

Max Range: 1.0673. Min Range: -1.0673

Max Act: 1.0673. Min Act: -0.0000

Data Index: 310386 (The Pile)

Max Activating Token Index: 287

Text #4

Max Range: 1.0673. Min Range: -1.0673

Max Act: 1.0196. Min Act: -0.0000

Data Index: 830068 (The Pile)

Max Activating Token Index: 368

Text #5

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1933121 (The Pile)

Max Activating Token Index: 683

Text #6

Max Range: 1.0673. Min Range: -1.0673

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1620141 (The Pile)

Max Activating Token Index: 1008

Text #7

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.9099. Min Act: -0.0000

Data Index: 217579 (The Pile)

Max Activating Token Index: 539

Text #8

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.9633. Min Act: -0.0000

Data Index: 1542629 (The Pile)

Max Activating Token Index: 380

Text #9

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.9901. Min Act: -0.0000

Data Index: 387202 (The Pile)

Max Activating Token Index: 187

Text #10

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.9332. Min Act: -0.0000

Data Index: 296154 (The Pile)

Max Activating Token Index: 476

Text #11

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8946. Min Act: -0.0000

Data Index: 459478 (The Pile)

Max Activating Token Index: 827

Text #12

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8875. Min Act: -0.0000

Data Index: 279870 (The Pile)

Max Activating Token Index: 182

Text #13

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.9354. Min Act: -0.0000

Data Index: 494542 (The Pile)

Max Activating Token Index: 904

Text #14

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.9341. Min Act: -0.0000

Data Index: 1519448 (The Pile)

Max Activating Token Index: 220

Text #15

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.9319. Min Act: -0.0000

Data Index: 1230794 (The Pile)

Max Activating Token Index: 832

Text #16

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.9271. Min Act: -0.0000

Data Index: 1630418 (The Pile)

Max Activating Token Index: 935

Text #17

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.9264. Min Act: -0.0000

Data Index: 415380 (The Pile)

Max Activating Token Index: 361

Text #18

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8898. Min Act: -0.0000

Data Index: 1857986 (The Pile)

Max Activating Token Index: 301

Text #19

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.9414. Min Act: -0.0000

Data Index: 1991841 (The Pile)

Max Activating Token Index: 390