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

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

Neuron 1290 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1412106 (Python Code)

Max Activating Token Index: 309

Text #1

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1576925 (Python Code)

Max Activating Token Index: 292

Text #2

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4129. Min Act: -0.0000

Data Index: 1369714 (Python Code)

Max Activating Token Index: 970

Text #3

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1587504 (Python Code)

Max Activating Token Index: 293

Text #4

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3759. Min Act: -0.0000

Data Index: 1409949 (Python Code)

Max Activating Token Index: 681

Text #5

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1643356 (Python Code)

Max Activating Token Index: 987

Text #6

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3429. Min Act: -0.0000

Data Index: 1605641 (Python Code)

Max Activating Token Index: 1015

Text #7

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1448496 (Python Code)

Max Activating Token Index: 296

Text #8

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1581457 (Python Code)

Max Activating Token Index: 378

Text #9

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3296. Min Act: -0.0000

Data Index: 1587466 (Python Code)

Max Activating Token Index: 335

Text #10

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3344. Min Act: -0.0000

Data Index: 1450917 (Python Code)

Max Activating Token Index: 739

Text #11

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1521370 (Python Code)

Max Activating Token Index: 569

Text #12

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1560361 (Python Code)

Max Activating Token Index: 964

Text #13

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3133. Min Act: -0.0000

Data Index: 1644779 (Python Code)

Max Activating Token Index: 562

Text #14

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.2910. Min Act: -0.0000

Data Index: 1366532 (Python Code)

Max Activating Token Index: 644

Text #15

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.2951. Min Act: -0.0000

Data Index: 1368693 (Python Code)

Max Activating Token Index: 901

Text #16

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1627053 (Python Code)

Max Activating Token Index: 892

Text #17

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1547742 (Python Code)

Max Activating Token Index: 130

Text #18

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.2915. Min Act: -0.0000

Data Index: 1550152 (Python Code)

Max Activating Token Index: 366

Text #19

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1568856 (Python Code)

Max Activating Token Index: 553