Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1294 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3146. Min Range: -3.3146

Max Act: 3.3146. Min Act: -0.0000

Data Index: 1321080 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 3.3146. Min Range: -3.3146

Max Act: 0.5299. Min Act: -0.0000

Data Index: 729827 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 3.3146. Min Range: -3.3146

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1094289 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 3.3146. Min Range: -3.3146

Max Act: 0.3366. Min Act: -0.0000

Data Index: 708036 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 3.3146. Min Range: -3.3146

Max Act: 0.0636. Min Act: -0.0000

Data Index: 70692 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 3.3146. Min Range: -3.3146

Max Act: 0.0571. Min Act: -0.0000

Data Index: 93450 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 3.3146. Min Range: -3.3146

Max Act: 0.0524. Min Act: -0.0000

Data Index: 478515 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 3.3146. Min Range: -3.3146

Max Act: 0.0497. Min Act: -0.0000

Data Index: 767070 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 3.3146. Min Range: -3.3146

Max Act: 0.0510. Min Act: -0.0000

Data Index: 141847 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 3.3146. Min Range: -3.3146

Max Act: 0.0499. Min Act: -0.0000

Data Index: 757370 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 3.3146. Min Range: -3.3146

Max Act: 0.0495. Min Act: -0.0000

Data Index: 1335659 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 3.3146. Min Range: -3.3146

Max Act: 0.0497. Min Act: -0.0000

Data Index: 676737 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 3.3146. Min Range: -3.3146

Max Act: 0.0533. Min Act: -0.0000

Data Index: 426547 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 3.3146. Min Range: -3.3146

Max Act: 0.0435. Min Act: -0.0000

Data Index: 82047 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 3.3146. Min Range: -3.3146

Max Act: 0.0463. Min Act: -0.0000

Data Index: 1186565 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 3.3146. Min Range: -3.3146

Max Act: 0.0455. Min Act: -0.0000

Data Index: 42675 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 3.3146. Min Range: -3.3146

Max Act: 0.0435. Min Act: -0.0000

Data Index: 706544 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 3.3146. Min Range: -3.3146

Max Act: 0.0438. Min Act: -0.0000

Data Index: 884717 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 3.3146. Min Range: -3.3146

Max Act: 0.0463. Min Act: -0.0000

Data Index: 1325039 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 3.3146. Min Range: -3.3146

Max Act: 0.0435. Min Act: -0.0000

Data Index: 238304 (C4 (Web Text))

Max Activating Token Index: 8