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

Dataset: The Pile

Neuron 1622 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3235. Min Act: -0.0000

Data Index: 389873 (The Pile)

Max Activating Token Index: 494

Text #1

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3073. Min Act: -0.0000

Data Index: 1031820 (The Pile)

Max Activating Token Index: 285

Text #2

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2892. Min Act: -0.0000

Data Index: 1190725 (The Pile)

Max Activating Token Index: 792

Text #3

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3453. Min Act: -0.0000

Data Index: 1970056 (The Pile)

Max Activating Token Index: 858

Text #4

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2815. Min Act: -0.0000

Data Index: 969912 (The Pile)

Max Activating Token Index: 575

Text #5

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3094. Min Act: -0.0000

Data Index: 1491922 (The Pile)

Max Activating Token Index: 558

Text #6

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2827. Min Act: -0.0000

Data Index: 1946609 (The Pile)

Max Activating Token Index: 614

Text #7

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1294510 (The Pile)

Max Activating Token Index: 418

Text #8

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2803. Min Act: -0.0000

Data Index: 161357 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2796. Min Act: -0.0000

Data Index: 1563252 (The Pile)

Max Activating Token Index: 628

Text #10

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2798. Min Act: -0.0000

Data Index: 680567 (The Pile)

Max Activating Token Index: 982

Text #11

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2512. Min Act: -0.0000

Data Index: 683618 (The Pile)

Max Activating Token Index: 491

Text #12

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2672. Min Act: -0.0000

Data Index: 1113249 (The Pile)

Max Activating Token Index: 550

Text #13

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2566. Min Act: -0.0000

Data Index: 1371920 (The Pile)

Max Activating Token Index: 1005

Text #14

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1528121 (The Pile)

Max Activating Token Index: 760

Text #15

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1661217 (The Pile)

Max Activating Token Index: 382

Text #16

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2267. Min Act: -0.0000

Data Index: 1399687 (The Pile)

Max Activating Token Index: 618

Text #17

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1915284 (The Pile)

Max Activating Token Index: 472

Text #18

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2573. Min Act: -0.0000

Data Index: 591420 (The Pile)

Max Activating Token Index: 923

Text #19

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2369. Min Act: -0.0000

Data Index: 933728 (The Pile)

Max Activating Token Index: 937