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

Dataset: The Pile

Neuron 4714 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.4411. Min Act: -0.0000

Data Index: 335977 (The Pile)

Max Activating Token Index: 910

Text #1

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.4514. Min Act: -0.0000

Data Index: 318420 (The Pile)

Max Activating Token Index: 670

Text #2

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3726. Min Act: -0.0000

Data Index: 1669009 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1624020 (The Pile)

Max Activating Token Index: 948

Text #4

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3595. Min Act: -0.0000

Data Index: 1361182 (The Pile)

Max Activating Token Index: 621

Text #5

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3416. Min Act: -0.0000

Data Index: 628198 (The Pile)

Max Activating Token Index: 547

Text #6

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1306382 (The Pile)

Max Activating Token Index: 484

Text #7

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3328. Min Act: -0.0000

Data Index: 474202 (The Pile)

Max Activating Token Index: 915

Text #8

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3411. Min Act: -0.0000

Data Index: 1764368 (The Pile)

Max Activating Token Index: 765

Text #9

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3084. Min Act: -0.0000

Data Index: 1628676 (The Pile)

Max Activating Token Index: 995

Text #10

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1376407 (The Pile)

Max Activating Token Index: 800

Text #11

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3118. Min Act: -0.0000

Data Index: 617017 (The Pile)

Max Activating Token Index: 391

Text #12

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.2937. Min Act: -0.0000

Data Index: 1320543 (The Pile)

Max Activating Token Index: 773

Text #13

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1189309 (The Pile)

Max Activating Token Index: 763

Text #14

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.2825. Min Act: -0.0000

Data Index: 786502 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.2741. Min Act: -0.0000

Data Index: 588054 (The Pile)

Max Activating Token Index: 1009

Text #16

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1675633 (The Pile)

Max Activating Token Index: 879

Text #17

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.2831. Min Act: -0.0000

Data Index: 362310 (The Pile)

Max Activating Token Index: 757

Text #18

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1123073 (The Pile)

Max Activating Token Index: 911

Text #19

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.2805. Min Act: -0.0000

Data Index: 174238 (The Pile)

Max Activating Token Index: 976