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

Dataset: The Pile

Neuron 46 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: 1.5734. Min Range: -1.5734

Max Act: 1.5734. Min Act: -0.0000

Data Index: 398446 (The Pile)

Max Activating Token Index: 55

Text #1

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.4502. Min Act: -0.0000

Data Index: 285144 (The Pile)

Max Activating Token Index: 227

Text #2

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.3633. Min Act: -0.0000

Data Index: 741938 (The Pile)

Max Activating Token Index: 258

Text #3

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.3545. Min Act: -0.0000

Data Index: 845513 (The Pile)

Max Activating Token Index: 194

Text #4

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.3467. Min Act: -0.0000

Data Index: 326441 (The Pile)

Max Activating Token Index: 265

Text #5

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.2650. Min Act: -0.0000

Data Index: 1502619 (The Pile)

Max Activating Token Index: 400

Text #6

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.4506. Min Act: -0.0000

Data Index: 762445 (The Pile)

Max Activating Token Index: 502

Text #7

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.1307. Min Act: -0.0000

Data Index: 779973 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.2105. Min Act: -0.0000

Data Index: 560424 (The Pile)

Max Activating Token Index: 235

Text #9

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.1345. Min Act: -0.0000

Data Index: 360293 (The Pile)

Max Activating Token Index: 103

Text #10

Max Range: 1.5734. Min Range: -1.5734

Max Act: 0.9728. Min Act: -0.0000

Data Index: 1572615 (The Pile)

Max Activating Token Index: 817

Text #11

Max Range: 1.5734. Min Range: -1.5734

Max Act: 0.9918. Min Act: -0.0000

Data Index: 1434676 (The Pile)

Max Activating Token Index: 870

Text #12

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.0520. Min Act: -0.0000

Data Index: 1078430 (The Pile)

Max Activating Token Index: 598

Text #13

Max Range: 1.5734. Min Range: -1.5734

Max Act: 0.9385. Min Act: -0.0000

Data Index: 1706512 (The Pile)

Max Activating Token Index: 473

Text #14

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.1228. Min Act: -0.0000

Data Index: 1033067 (The Pile)

Max Activating Token Index: 773

Text #15

Max Range: 1.5734. Min Range: -1.5734

Max Act: 0.8348. Min Act: -0.0000

Data Index: 840761 (The Pile)

Max Activating Token Index: 151

Text #16

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.0182. Min Act: -0.0000

Data Index: 201350 (The Pile)

Max Activating Token Index: 951

Text #17

Max Range: 1.5734. Min Range: -1.5734

Max Act: 0.8409. Min Act: -0.0000

Data Index: 1592686 (The Pile)

Max Activating Token Index: 960

Text #18

Max Range: 1.5734. Min Range: -1.5734

Max Act: 0.7745. Min Act: -0.0000

Data Index: 1701751 (The Pile)

Max Activating Token Index: 172

Text #19

Max Range: 1.5734. Min Range: -1.5734

Max Act: 0.7688. Min Act: -0.0000

Data Index: 473864 (The Pile)

Max Activating Token Index: 695