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

Dataset: The Pile

Neuron 1716 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: 1.6851. Min Range: -1.6851

Max Act: 1.6851. Min Act: -0.0000

Data Index: 1193748 (The Pile)

Max Activating Token Index: 403

Text #1

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.4152. Min Act: -0.0000

Data Index: 1263687 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.3263. Min Act: -0.0000

Data Index: 1617886 (The Pile)

Max Activating Token Index: 306

Text #3

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.3866. Min Act: -0.0000

Data Index: 408165 (The Pile)

Max Activating Token Index: 369

Text #4

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.4629. Min Act: -0.0000

Data Index: 1233269 (The Pile)

Max Activating Token Index: 193

Text #5

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.3705. Min Act: -0.0000

Data Index: 858421 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.3876. Min Act: -0.0000

Data Index: 1053540 (The Pile)

Max Activating Token Index: 476

Text #7

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.3287. Min Act: -0.0000

Data Index: 321457 (The Pile)

Max Activating Token Index: 510

Text #8

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.3226. Min Act: -0.0000

Data Index: 1550756 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.2651. Min Act: -0.0000

Data Index: 206881 (The Pile)

Max Activating Token Index: 958

Text #10

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.3107. Min Act: -0.0000

Data Index: 119843 (The Pile)

Max Activating Token Index: 319

Text #11

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.1815. Min Act: -0.0000

Data Index: 1175138 (The Pile)

Max Activating Token Index: 410

Text #12

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.2413. Min Act: -0.0000

Data Index: 1655835 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.2046. Min Act: -0.0000

Data Index: 1647738 (The Pile)

Max Activating Token Index: 472

Text #14

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.1185. Min Act: -0.0000

Data Index: 686119 (The Pile)

Max Activating Token Index: 885

Text #15

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.2145. Min Act: -0.0000

Data Index: 1942891 (The Pile)

Max Activating Token Index: 600

Text #16

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.1684. Min Act: -0.0000

Data Index: 1273177 (The Pile)

Max Activating Token Index: 326

Text #17

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.0822. Min Act: -0.0000

Data Index: 57345 (The Pile)

Max Activating Token Index: 676

Text #18

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.1038. Min Act: -0.0000

Data Index: 1441958 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 1.6851. Min Range: -1.6851

Max Act: 1.0938. Min Act: -0.0000

Data Index: 1778484 (The Pile)

Max Activating Token Index: 182