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

Dataset: The Pile

Neuron 1192 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.8075. Min Act: 0.0000

Data Index: 663941 (The Pile)

Max Activating Token Index: 590

Text #1

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1584322 (The Pile)

Max Activating Token Index: 287

Text #2

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6937. Min Act: -0.0000

Data Index: 651877 (The Pile)

Max Activating Token Index: 839

Text #3

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6696. Min Act: -0.0000

Data Index: 544790 (The Pile)

Max Activating Token Index: 67

Text #4

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6433. Min Act: -0.0000

Data Index: 171669 (The Pile)

Max Activating Token Index: 813

Text #5

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.7566. Min Act: -0.0000

Data Index: 987753 (The Pile)

Max Activating Token Index: 553

Text #6

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5595. Min Act: -0.0000

Data Index: 636295 (The Pile)

Max Activating Token Index: 593

Text #7

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1763496 (The Pile)

Max Activating Token Index: 714

Text #8

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6784. Min Act: -0.0000

Data Index: 1631708 (The Pile)

Max Activating Token Index: 66

Text #9

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6711. Min Act: -0.0000

Data Index: 151122 (The Pile)

Max Activating Token Index: 132

Text #10

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1036725 (The Pile)

Max Activating Token Index: 725

Text #11

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1852233 (The Pile)

Max Activating Token Index: 315

Text #12

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6274. Min Act: -0.0000

Data Index: 674303 (The Pile)

Max Activating Token Index: 953

Text #13

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6105. Min Act: -0.0000

Data Index: 140078 (The Pile)

Max Activating Token Index: 631

Text #14

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.7014. Min Act: -0.0000

Data Index: 717515 (The Pile)

Max Activating Token Index: 221

Text #15

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6351. Min Act: -0.0000

Data Index: 224783 (The Pile)

Max Activating Token Index: 831

Text #16

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1021892 (The Pile)

Max Activating Token Index: 688

Text #17

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6437. Min Act: -0.0000

Data Index: 682580 (The Pile)

Max Activating Token Index: 763

Text #18

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1901066 (The Pile)

Max Activating Token Index: 965

Text #19

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6369. Min Act: -0.0000

Data Index: 1950474 (The Pile)

Max Activating Token Index: 317