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

Dataset: The Pile

Neuron 2944 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: 0.0656. Min Range: -0.0656

Max Act: 0.0656. Min Act: -0.0000

Data Index: 1278464 (The Pile)

Max Activating Token Index: 935

Text #1

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0420. Min Act: -0.0000

Data Index: 1724991 (The Pile)

Max Activating Token Index: 135

Text #2

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0539. Min Act: -0.0000

Data Index: 524788 (The Pile)

Max Activating Token Index: 253

Text #3

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0462. Min Act: -0.0000

Data Index: 806137 (The Pile)

Max Activating Token Index: 262

Text #4

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0488. Min Act: -0.0000

Data Index: 285292 (The Pile)

Max Activating Token Index: 181

Text #5

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0489. Min Act: -0.0000

Data Index: 944912 (The Pile)

Max Activating Token Index: 426

Text #6

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0451. Min Act: -0.0000

Data Index: 989126 (The Pile)

Max Activating Token Index: 576

Text #7

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0484. Min Act: -0.0000

Data Index: 187878 (The Pile)

Max Activating Token Index: 204

Text #8

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0466. Min Act: -0.0000

Data Index: 858248 (The Pile)

Max Activating Token Index: 894

Text #9

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0472. Min Act: -0.0000

Data Index: 1680553 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0439. Min Act: -0.0000

Data Index: 604934 (The Pile)

Max Activating Token Index: 213

Text #11

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0430. Min Act: -0.0000

Data Index: 362125 (The Pile)

Max Activating Token Index: 723

Text #12

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0498. Min Act: -0.0000

Data Index: 1781643 (The Pile)

Max Activating Token Index: 602

Text #13

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0464. Min Act: -0.0000

Data Index: 856149 (The Pile)

Max Activating Token Index: 619

Text #14

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0390. Min Act: -0.0000

Data Index: 883119 (The Pile)

Max Activating Token Index: 570

Text #15

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0459. Min Act: -0.0000

Data Index: 1789671 (The Pile)

Max Activating Token Index: 250

Text #16

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0443. Min Act: -0.0000

Data Index: 1324879 (The Pile)

Max Activating Token Index: 504

Text #17

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0419. Min Act: -0.0000

Data Index: 493773 (The Pile)

Max Activating Token Index: 703

Text #18

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0438. Min Act: -0.0000

Data Index: 21422 (The Pile)

Max Activating Token Index: 235

Text #19

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0422. Min Act: -0.0000

Data Index: 1360798 (The Pile)

Max Activating Token Index: 1002