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

Dataset: The Pile

Neuron 3069 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: 5.2494. Min Range: -5.2494

Max Act: 5.2494. Min Act: -0.0000

Data Index: 39734 (The Pile)

Max Activating Token Index: 319

Text #1

Max Range: 5.2494. Min Range: -5.2494

Max Act: 3.4879. Min Act: -0.0000

Data Index: 673545 (The Pile)

Max Activating Token Index: 945

Text #2

Max Range: 5.2494. Min Range: -5.2494

Max Act: 2.8731. Min Act: -0.0000

Data Index: 1490374 (The Pile)

Max Activating Token Index: 160

Text #3

Max Range: 5.2494. Min Range: -5.2494

Max Act: 3.0905. Min Act: -0.0000

Data Index: 576493 (The Pile)

Max Activating Token Index: 227

Text #4

Max Range: 5.2494. Min Range: -5.2494

Max Act: 3.0777. Min Act: -0.0000

Data Index: 742362 (The Pile)

Max Activating Token Index: 43

Text #5

Max Range: 5.2494. Min Range: -5.2494

Max Act: 3.3359. Min Act: -0.0000

Data Index: 395293 (The Pile)

Max Activating Token Index: 604

Text #6

Max Range: 5.2494. Min Range: -5.2494

Max Act: 2.6856. Min Act: -0.0000

Data Index: 818213 (The Pile)

Max Activating Token Index: 714

Text #7

Max Range: 5.2494. Min Range: -5.2494

Max Act: 3.2096. Min Act: -0.0000

Data Index: 1690665 (The Pile)

Max Activating Token Index: 721

Text #8

Max Range: 5.2494. Min Range: -5.2494

Max Act: 2.7829. Min Act: -0.0000

Data Index: 1568741 (The Pile)

Max Activating Token Index: 833

Text #9

Max Range: 5.2494. Min Range: -5.2494

Max Act: 3.0016. Min Act: -0.0000

Data Index: 9366 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 5.2494. Min Range: -5.2494

Max Act: 2.8467. Min Act: -0.0000

Data Index: 715181 (The Pile)

Max Activating Token Index: 517

Text #11

Max Range: 5.2494. Min Range: -5.2494

Max Act: 2.6435. Min Act: -0.0000

Data Index: 1160876 (The Pile)

Max Activating Token Index: 408

Text #12

Max Range: 5.2494. Min Range: -5.2494

Max Act: 2.5526. Min Act: -0.0000

Data Index: 567287 (The Pile)

Max Activating Token Index: 712

Text #13

Max Range: 5.2494. Min Range: -5.2494

Max Act: 2.9860. Min Act: -0.0000

Data Index: 186481 (The Pile)

Max Activating Token Index: 963

Text #14

Max Range: 5.2494. Min Range: -5.2494

Max Act: 2.9121. Min Act: -0.0000

Data Index: 1682058 (The Pile)

Max Activating Token Index: 209

Text #15

Max Range: 5.2494. Min Range: -5.2494

Max Act: 2.5432. Min Act: -0.0000

Data Index: 1933989 (The Pile)

Max Activating Token Index: 175

Text #16

Max Range: 5.2494. Min Range: -5.2494

Max Act: 2.5171. Min Act: -0.0000

Data Index: 230837 (The Pile)

Max Activating Token Index: 479

Text #17

Max Range: 5.2494. Min Range: -5.2494

Max Act: 2.7788. Min Act: -0.0000

Data Index: 516395 (The Pile)

Max Activating Token Index: 231

Text #18

Max Range: 5.2494. Min Range: -5.2494

Max Act: 2.6146. Min Act: -0.0000

Data Index: 1543879 (The Pile)

Max Activating Token Index: 404

Text #19

Max Range: 5.2494. Min Range: -5.2494

Max Act: 2.4990. Min Act: -0.0000

Data Index: 1228490 (The Pile)

Max Activating Token Index: 49