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

Dataset: The Pile

Neuron 4574 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.8389. Min Act: -0.0000

Data Index: 589066 (The Pile)

Max Activating Token Index: 336

Text #1

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.6806. Min Act: -0.0000

Data Index: 1391359 (The Pile)

Max Activating Token Index: 941

Text #2

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.6974. Min Act: -0.0000

Data Index: 1766675 (The Pile)

Max Activating Token Index: 22

Text #3

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1833117 (The Pile)

Max Activating Token Index: 845

Text #4

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.6444. Min Act: -0.0000

Data Index: 567367 (The Pile)

Max Activating Token Index: 738

Text #5

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.6426. Min Act: -0.0000

Data Index: 250370 (The Pile)

Max Activating Token Index: 950

Text #6

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.6205. Min Act: -0.0000

Data Index: 1032567 (The Pile)

Max Activating Token Index: 949

Text #7

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5774. Min Act: -0.0000

Data Index: 1497377 (The Pile)

Max Activating Token Index: 488

Text #8

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5851. Min Act: -0.0000

Data Index: 188970 (The Pile)

Max Activating Token Index: 525

Text #9

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1377656 (The Pile)

Max Activating Token Index: 614

Text #10

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5812. Min Act: -0.0000

Data Index: 1949202 (The Pile)

Max Activating Token Index: 1014

Text #11

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.4722. Min Act: -0.0000

Data Index: 1123960 (The Pile)

Max Activating Token Index: 971

Text #12

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1784148 (The Pile)

Max Activating Token Index: 688

Text #13

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5283. Min Act: -0.0000

Data Index: 272654 (The Pile)

Max Activating Token Index: 690

Text #14

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.4837. Min Act: -0.0000

Data Index: 538003 (The Pile)

Max Activating Token Index: 113

Text #15

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1126171 (The Pile)

Max Activating Token Index: 959

Text #16

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1794878 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5264. Min Act: -0.0000

Data Index: 329864 (The Pile)

Max Activating Token Index: 601

Text #18

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5009. Min Act: -0.0000

Data Index: 246892 (The Pile)

Max Activating Token Index: 645

Text #19

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5212. Min Act: -0.0000

Data Index: 774988 (The Pile)

Max Activating Token Index: 422