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

Dataset: The Pile

Neuron 2231 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: 1.4884. Min Range: -1.4884

Max Act: 1.4150. Min Act: -0.0000

Data Index: 1455785 (The Pile)

Max Activating Token Index: 884

Text #1

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.4136. Min Act: -0.0000

Data Index: 1541083 (The Pile)

Max Activating Token Index: 429

Text #2

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.4884. Min Act: -0.0000

Data Index: 648550 (The Pile)

Max Activating Token Index: 26

Text #3

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.2665. Min Act: -0.0000

Data Index: 1008681 (The Pile)

Max Activating Token Index: 15

Text #4

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.3416. Min Act: -0.0000

Data Index: 807844 (The Pile)

Max Activating Token Index: 259

Text #5

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1407. Min Act: -0.0000

Data Index: 1261585 (The Pile)

Max Activating Token Index: 754

Text #6

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1712. Min Act: -0.0000

Data Index: 470538 (The Pile)

Max Activating Token Index: 794

Text #7

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.2110. Min Act: -0.0000

Data Index: 878607 (The Pile)

Max Activating Token Index: 1015

Text #8

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1868. Min Act: -0.0000

Data Index: 1979773 (The Pile)

Max Activating Token Index: 561

Text #9

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1825. Min Act: -0.0000

Data Index: 1822937 (The Pile)

Max Activating Token Index: 207

Text #10

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.3551. Min Act: -0.0000

Data Index: 1329538 (The Pile)

Max Activating Token Index: 879

Text #11

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1677. Min Act: -0.0000

Data Index: 1716480 (The Pile)

Max Activating Token Index: 853

Text #12

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1624. Min Act: -0.0000

Data Index: 1429418 (The Pile)

Max Activating Token Index: 751

Text #13

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.0901. Min Act: -0.0000

Data Index: 889622 (The Pile)

Max Activating Token Index: 574

Text #14

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1186. Min Act: -0.0000

Data Index: 13848 (The Pile)

Max Activating Token Index: 14

Text #15

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.0925. Min Act: -0.0000

Data Index: 1559774 (The Pile)

Max Activating Token Index: 133

Text #16

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.0519. Min Act: -0.0000

Data Index: 346751 (The Pile)

Max Activating Token Index: 819

Text #17

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.0121. Min Act: -0.0000

Data Index: 1162048 (The Pile)

Max Activating Token Index: 1010

Text #18

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.0600. Min Act: -0.0000

Data Index: 1683223 (The Pile)

Max Activating Token Index: 917

Text #19

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1280. Min Act: -0.0000

Data Index: 1919276 (The Pile)

Max Activating Token Index: 87