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

Dataset: The Pile

Neuron 2432 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: 1.1508. Min Range: -1.1508

Max Act: 1.1508. Min Act: -0.0000

Data Index: 1506686 (The Pile)

Max Activating Token Index: 178

Text #1

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.7826. Min Act: -0.0000

Data Index: 853828 (The Pile)

Max Activating Token Index: 993

Text #2

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.7217. Min Act: -0.0000

Data Index: 1320065 (The Pile)

Max Activating Token Index: 330

Text #3

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.7087. Min Act: -0.0000

Data Index: 1328038 (The Pile)

Max Activating Token Index: 888

Text #4

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.7347. Min Act: -0.0000

Data Index: 481470 (The Pile)

Max Activating Token Index: 641

Text #5

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.7719. Min Act: -0.0000

Data Index: 1117875 (The Pile)

Max Activating Token Index: 709

Text #6

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.6477. Min Act: -0.0000

Data Index: 418981 (The Pile)

Max Activating Token Index: 996

Text #7

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.6440. Min Act: -0.0000

Data Index: 346458 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.7018. Min Act: -0.0000

Data Index: 1211824 (The Pile)

Max Activating Token Index: 126

Text #9

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1971497 (The Pile)

Max Activating Token Index: 543

Text #10

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.6134. Min Act: -0.0000

Data Index: 1258830 (The Pile)

Max Activating Token Index: 181

Text #11

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.6269. Min Act: -0.0000

Data Index: 953152 (The Pile)

Max Activating Token Index: 878

Text #12

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.6283. Min Act: -0.0000

Data Index: 750166 (The Pile)

Max Activating Token Index: 817

Text #13

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.7056. Min Act: -0.0000

Data Index: 650367 (The Pile)

Max Activating Token Index: 465

Text #14

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1635986 (The Pile)

Max Activating Token Index: 391

Text #15

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1275098 (The Pile)

Max Activating Token Index: 586

Text #16

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.5480. Min Act: -0.0000

Data Index: 132159 (The Pile)

Max Activating Token Index: 990

Text #17

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.6014. Min Act: -0.0000

Data Index: 620885 (The Pile)

Max Activating Token Index: 395

Text #18

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.5810. Min Act: -0.0000

Data Index: 477998 (The Pile)

Max Activating Token Index: 591

Text #19

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.6287. Min Act: -0.0000

Data Index: 878868 (The Pile)

Max Activating Token Index: 759