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

Dataset: The Pile

Neuron 787 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: 0.8330. Min Range: -0.8330

Max Act: 0.7928. Min Act: -0.0000

Data Index: 312465 (The Pile)

Max Activating Token Index: 631

Text #1

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.8090. Min Act: -0.0000

Data Index: 1006412 (The Pile)

Max Activating Token Index: 339

Text #2

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.8330. Min Act: -0.0000

Data Index: 1107514 (The Pile)

Max Activating Token Index: 532

Text #3

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1399757 (The Pile)

Max Activating Token Index: 68

Text #4

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7427. Min Act: -0.0000

Data Index: 506355 (The Pile)

Max Activating Token Index: 925

Text #5

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.8105. Min Act: -0.0000

Data Index: 935523 (The Pile)

Max Activating Token Index: 215

Text #6

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7569. Min Act: -0.0000

Data Index: 1542404 (The Pile)

Max Activating Token Index: 196

Text #7

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7611. Min Act: -0.0000

Data Index: 285094 (The Pile)

Max Activating Token Index: 350

Text #8

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7590. Min Act: -0.0000

Data Index: 1110505 (The Pile)

Max Activating Token Index: 916

Text #9

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1303364 (The Pile)

Max Activating Token Index: 700

Text #10

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1846151 (The Pile)

Max Activating Token Index: 619

Text #11

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1251976 (The Pile)

Max Activating Token Index: 461

Text #12

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6533. Min Act: -0.0000

Data Index: 788725 (The Pile)

Max Activating Token Index: 496

Text #13

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6291. Min Act: -0.0000

Data Index: 1782853 (The Pile)

Max Activating Token Index: 454

Text #14

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1165902 (The Pile)

Max Activating Token Index: 884

Text #15

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5924. Min Act: -0.0000

Data Index: 268726 (The Pile)

Max Activating Token Index: 99

Text #16

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6322. Min Act: -0.0000

Data Index: 1513417 (The Pile)

Max Activating Token Index: 36

Text #17

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6036. Min Act: -0.0000

Data Index: 541999 (The Pile)

Max Activating Token Index: 316

Text #18

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6659. Min Act: -0.0000

Data Index: 899885 (The Pile)

Max Activating Token Index: 500

Text #19

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6382. Min Act: -0.0000

Data Index: 122520 (The Pile)

Max Activating Token Index: 460