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

Dataset: The Pile

Neuron 3523 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: 1.3413. Min Range: -1.3413

Max Act: 1.3413. Min Act: -0.0000

Data Index: 1307725 (The Pile)

Max Activating Token Index: 473

Text #1

Max Range: 1.3413. Min Range: -1.3413

Max Act: 1.2495. Min Act: -0.0000

Data Index: 397039 (The Pile)

Max Activating Token Index: 920

Text #2

Max Range: 1.3413. Min Range: -1.3413

Max Act: 1.1073. Min Act: -0.0000

Data Index: 21560 (The Pile)

Max Activating Token Index: 550

Text #3

Max Range: 1.3413. Min Range: -1.3413

Max Act: 1.1201. Min Act: -0.0000

Data Index: 151952 (The Pile)

Max Activating Token Index: 207

Text #4

Max Range: 1.3413. Min Range: -1.3413

Max Act: 1.1129. Min Act: -0.0000

Data Index: 1875680 (The Pile)

Max Activating Token Index: 651

Text #5

Max Range: 1.3413. Min Range: -1.3413

Max Act: 1.1600. Min Act: -0.0000

Data Index: 1620673 (The Pile)

Max Activating Token Index: 375

Text #6

Max Range: 1.3413. Min Range: -1.3413

Max Act: 1.0790. Min Act: -0.0000

Data Index: 1817745 (The Pile)

Max Activating Token Index: 432

Text #7

Max Range: 1.3413. Min Range: -1.3413

Max Act: 1.0489. Min Act: -0.0000

Data Index: 855582 (The Pile)

Max Activating Token Index: 625

Text #8

Max Range: 1.3413. Min Range: -1.3413

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1367881 (The Pile)

Max Activating Token Index: 408

Text #9

Max Range: 1.3413. Min Range: -1.3413

Max Act: 0.9158. Min Act: 0.0000

Data Index: 1859377 (The Pile)

Max Activating Token Index: 295

Text #10

Max Range: 1.3413. Min Range: -1.3413

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1082923 (The Pile)

Max Activating Token Index: 46

Text #11

Max Range: 1.3413. Min Range: -1.3413

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1088948 (The Pile)

Max Activating Token Index: 889

Text #12

Max Range: 1.3413. Min Range: -1.3413

Max Act: 0.9824. Min Act: -0.0000

Data Index: 1518866 (The Pile)

Max Activating Token Index: 597

Text #13

Max Range: 1.3413. Min Range: -1.3413

Max Act: 0.9193. Min Act: -0.0000

Data Index: 1926408 (The Pile)

Max Activating Token Index: 505

Text #14

Max Range: 1.3413. Min Range: -1.3413

Max Act: 0.9243. Min Act: -0.0000

Data Index: 628251 (The Pile)

Max Activating Token Index: 731

Text #15

Max Range: 1.3413. Min Range: -1.3413

Max Act: 0.9183. Min Act: -0.0000

Data Index: 844382 (The Pile)

Max Activating Token Index: 431

Text #16

Max Range: 1.3413. Min Range: -1.3413

Max Act: 0.9538. Min Act: -0.0000

Data Index: 826061 (The Pile)

Max Activating Token Index: 922

Text #17

Max Range: 1.3413. Min Range: -1.3413

Max Act: 0.9522. Min Act: -0.0000

Data Index: 1978521 (The Pile)

Max Activating Token Index: 205

Text #18

Max Range: 1.3413. Min Range: -1.3413

Max Act: 0.9296. Min Act: -0.0000

Data Index: 1950595 (The Pile)

Max Activating Token Index: 676

Text #19

Max Range: 1.3413. Min Range: -1.3413

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1201406 (The Pile)

Max Activating Token Index: 833