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

Dataset: The Pile

Neuron 1176 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: 0.8453. Min Range: -0.8453

Max Act: 0.7931. Min Act: -0.0000

Data Index: 354084 (The Pile)

Max Activating Token Index: 614

Text #1

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.8453. Min Act: -0.0000

Data Index: 1558004 (The Pile)

Max Activating Token Index: 305

Text #2

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1675677 (The Pile)

Max Activating Token Index: 922

Text #3

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6582. Min Act: -0.0000

Data Index: 1949123 (The Pile)

Max Activating Token Index: 298

Text #4

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6100. Min Act: -0.0000

Data Index: 1358286 (The Pile)

Max Activating Token Index: 407

Text #5

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5974. Min Act: -0.0000

Data Index: 1969618 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6198. Min Act: -0.0000

Data Index: 582070 (The Pile)

Max Activating Token Index: 184

Text #7

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1847338 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1516293 (The Pile)

Max Activating Token Index: 509

Text #9

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6151. Min Act: -0.0000

Data Index: 160519 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5815. Min Act: -0.0000

Data Index: 1343441 (The Pile)

Max Activating Token Index: 772

Text #11

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5922. Min Act: -0.0000

Data Index: 276410 (The Pile)

Max Activating Token Index: 444

Text #12

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5456. Min Act: -0.0000

Data Index: 482455 (The Pile)

Max Activating Token Index: 215

Text #13

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1234437 (The Pile)

Max Activating Token Index: 659

Text #14

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1302851 (The Pile)

Max Activating Token Index: 343

Text #15

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5330. Min Act: -0.0000

Data Index: 1134041 (The Pile)

Max Activating Token Index: 480

Text #16

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5806. Min Act: -0.0000

Data Index: 889279 (The Pile)

Max Activating Token Index: 68

Text #17

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5460. Min Act: -0.0000

Data Index: 400668 (The Pile)

Max Activating Token Index: 391

Text #18

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6027. Min Act: -0.0000

Data Index: 68344 (The Pile)

Max Activating Token Index: 235

Text #19

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5105. Min Act: -0.0000

Data Index: 607144 (The Pile)

Max Activating Token Index: 520