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

Dataset: The Pile

Neuron 608 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1691821 (The Pile)

Max Activating Token Index: 444

Text #1

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.4083. Min Act: -0.0000

Data Index: 684601 (The Pile)

Max Activating Token Index: 910

Text #2

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.4797. Min Act: -0.0000

Data Index: 66325 (The Pile)

Max Activating Token Index: 976

Text #3

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.3620. Min Act: -0.0000

Data Index: 272055 (The Pile)

Max Activating Token Index: 784

Text #4

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1140795 (The Pile)

Max Activating Token Index: 247

Text #5

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.3494. Min Act: -0.0000

Data Index: 161510 (The Pile)

Max Activating Token Index: 328

Text #6

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1606276 (The Pile)

Max Activating Token Index: 168

Text #7

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1539256 (The Pile)

Max Activating Token Index: 471

Text #8

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.3164. Min Act: -0.0000

Data Index: 824153 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.2963. Min Act: -0.0000

Data Index: 254309 (The Pile)

Max Activating Token Index: 138

Text #10

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.2252. Min Act: -0.0000

Data Index: 1403862 (The Pile)

Max Activating Token Index: 398

Text #11

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1785864 (The Pile)

Max Activating Token Index: 835

Text #12

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1990195 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1409906 (The Pile)

Max Activating Token Index: 137

Text #14

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.2812. Min Act: -0.0000

Data Index: 1646520 (The Pile)

Max Activating Token Index: 421

Text #15

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1772667 (The Pile)

Max Activating Token Index: 874

Text #16

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.2885. Min Act: -0.0000

Data Index: 290903 (The Pile)

Max Activating Token Index: 768

Text #17

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1920099 (The Pile)

Max Activating Token Index: 65

Text #18

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.2319. Min Act: -0.0000

Data Index: 1179561 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1045122 (The Pile)

Max Activating Token Index: 847