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

Dataset: The Pile

Neuron 1143 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: 1.7894. Min Range: -1.7894

Max Act: 1.7894. Min Act: -0.0000

Data Index: 1351376 (The Pile)

Max Activating Token Index: 1002

Text #1

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.5728. Min Act: -0.0000

Data Index: 50788 (The Pile)

Max Activating Token Index: 285

Text #2

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.2282. Min Act: -0.0000

Data Index: 673585 (The Pile)

Max Activating Token Index: 820

Text #3

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.0788. Min Act: -0.0000

Data Index: 1692789 (The Pile)

Max Activating Token Index: 855

Text #4

Max Range: 1.7894. Min Range: -1.7894

Max Act: 0.9142. Min Act: -0.0000

Data Index: 632168 (The Pile)

Max Activating Token Index: 966

Text #5

Max Range: 1.7894. Min Range: -1.7894

Max Act: 0.9694. Min Act: -0.0000

Data Index: 765876 (The Pile)

Max Activating Token Index: 1006

Text #6

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.0089. Min Act: -0.0000

Data Index: 1010576 (The Pile)

Max Activating Token Index: 799

Text #7

Max Range: 1.7894. Min Range: -1.7894

Max Act: 0.9407. Min Act: -0.0000

Data Index: 892 (The Pile)

Max Activating Token Index: 814

Text #8

Max Range: 1.7894. Min Range: -1.7894

Max Act: 0.9287. Min Act: -0.0000

Data Index: 1810807 (The Pile)

Max Activating Token Index: 779

Text #9

Max Range: 1.7894. Min Range: -1.7894

Max Act: 0.8152. Min Act: -0.0000

Data Index: 305204 (The Pile)

Max Activating Token Index: 683

Text #10

Max Range: 1.7894. Min Range: -1.7894

Max Act: 0.7834. Min Act: -0.0000

Data Index: 441671 (The Pile)

Max Activating Token Index: 756

Text #11

Max Range: 1.7894. Min Range: -1.7894

Max Act: 0.8485. Min Act: -0.0000

Data Index: 964140 (The Pile)

Max Activating Token Index: 926

Text #12

Max Range: 1.7894. Min Range: -1.7894

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1995741 (The Pile)

Max Activating Token Index: 261

Text #13

Max Range: 1.7894. Min Range: -1.7894

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1029419 (The Pile)

Max Activating Token Index: 776

Text #14

Max Range: 1.7894. Min Range: -1.7894

Max Act: 0.8301. Min Act: -0.0000

Data Index: 477166 (The Pile)

Max Activating Token Index: 574

Text #15

Max Range: 1.7894. Min Range: -1.7894

Max Act: 0.8598. Min Act: -0.0000

Data Index: 1763838 (The Pile)

Max Activating Token Index: 825

Text #16

Max Range: 1.7894. Min Range: -1.7894

Max Act: 0.8344. Min Act: -0.0000

Data Index: 990751 (The Pile)

Max Activating Token Index: 238

Text #17

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.0480. Min Act: -0.0000

Data Index: 387997 (The Pile)

Max Activating Token Index: 684

Text #18

Max Range: 1.7894. Min Range: -1.7894

Max Act: 0.8438. Min Act: -0.0000

Data Index: 481018 (The Pile)

Max Activating Token Index: 78

Text #19

Max Range: 1.7894. Min Range: -1.7894

Max Act: 0.8454. Min Act: -0.0000

Data Index: 1679278 (The Pile)

Max Activating Token Index: 221