Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 974 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3586. Min Range: -1.3586

Max Act: 1.3586. Min Act: -0.0000

Data Index: 475974 (The Pile)

Max Activating Token Index: 714

Text #1

Max Range: 1.3586. Min Range: -1.3586

Max Act: 1.1920. Min Act: -0.0000

Data Index: 676256 (The Pile)

Max Activating Token Index: 730

Text #2

Max Range: 1.3586. Min Range: -1.3586

Max Act: 1.1437. Min Act: -0.0000

Data Index: 122026 (The Pile)

Max Activating Token Index: 885

Text #3

Max Range: 1.3586. Min Range: -1.3586

Max Act: 1.0988. Min Act: -0.0000

Data Index: 1187053 (The Pile)

Max Activating Token Index: 1001

Text #4

Max Range: 1.3586. Min Range: -1.3586

Max Act: 1.1426. Min Act: -0.0000

Data Index: 831496 (The Pile)

Max Activating Token Index: 162

Text #5

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.8115. Min Act: -0.0000

Data Index: 160570 (The Pile)

Max Activating Token Index: 1001

Text #6

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.9858. Min Act: -0.0000

Data Index: 853699 (The Pile)

Max Activating Token Index: 269

Text #7

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.9677. Min Act: -0.0000

Data Index: 202247 (The Pile)

Max Activating Token Index: 1010

Text #8

Max Range: 1.3586. Min Range: -1.3586

Max Act: 1.0221. Min Act: -0.0000

Data Index: 1676734 (The Pile)

Max Activating Token Index: 21

Text #9

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.9063. Min Act: -0.0000

Data Index: 79875 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.9354. Min Act: -0.0000

Data Index: 1655091 (The Pile)

Max Activating Token Index: 56

Text #11

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.9727. Min Act: -0.0000

Data Index: 1818173 (The Pile)

Max Activating Token Index: 948

Text #12

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.8497. Min Act: -0.0000

Data Index: 29652 (The Pile)

Max Activating Token Index: 309

Text #13

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.9762. Min Act: -0.0000

Data Index: 1772182 (The Pile)

Max Activating Token Index: 822

Text #14

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1608423 (The Pile)

Max Activating Token Index: 212

Text #15

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.8098. Min Act: -0.0000

Data Index: 1912128 (The Pile)

Max Activating Token Index: 748

Text #16

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.8356. Min Act: -0.0000

Data Index: 1052377 (The Pile)

Max Activating Token Index: 646

Text #17

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.8935. Min Act: -0.0000

Data Index: 1815135 (The Pile)

Max Activating Token Index: 613

Text #18

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.8563. Min Act: -0.0000

Data Index: 873261 (The Pile)

Max Activating Token Index: 533

Text #19

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1713599 (The Pile)

Max Activating Token Index: 44