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

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

Neuron 4079 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3667. Min Range: -6.3667

Max Act: 6.3667. Min Act: -0.0000

Data Index: 54803 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 6.3667. Min Range: -6.3667

Max Act: 5.9432. Min Act: -0.0000

Data Index: 881574 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 6.3667. Min Range: -6.3667

Max Act: 5.3914. Min Act: -0.0000

Data Index: 1411356 (Python Code)

Max Activating Token Index: 424

Text #3

Max Range: 6.3667. Min Range: -6.3667

Max Act: 5.2289. Min Act: -0.0000

Data Index: 1562048 (Python Code)

Max Activating Token Index: 247

Text #4

Max Range: 6.3667. Min Range: -6.3667

Max Act: 3.8140. Min Act: -0.0000

Data Index: 876962 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 6.3667. Min Range: -6.3667

Max Act: 3.8343. Min Act: -0.0000

Data Index: 403973 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 6.3667. Min Range: -6.3667

Max Act: 3.6646. Min Act: -0.0000

Data Index: 1241367 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 6.3667. Min Range: -6.3667

Max Act: 3.5272. Min Act: -0.0000

Data Index: 51843 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 6.3667. Min Range: -6.3667

Max Act: 3.8003. Min Act: -0.0000

Data Index: 373422 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 6.3667. Min Range: -6.3667

Max Act: 3.6531. Min Act: -0.0000

Data Index: 1457755 (Python Code)

Max Activating Token Index: 320

Text #10

Max Range: 6.3667. Min Range: -6.3667

Max Act: 3.6377. Min Act: -0.0000

Data Index: 529152 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 6.3667. Min Range: -6.3667

Max Act: 3.6445. Min Act: -0.0000

Data Index: 407099 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 6.3667. Min Range: -6.3667

Max Act: 3.4455. Min Act: -0.0000

Data Index: 1441178 (Python Code)

Max Activating Token Index: 606

Text #13

Max Range: 6.3667. Min Range: -6.3667

Max Act: 3.6497. Min Act: -0.0000

Data Index: 407271 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 6.3667. Min Range: -6.3667

Max Act: 3.5875. Min Act: -0.0000

Data Index: 1114804 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 6.3667. Min Range: -6.3667

Max Act: 3.6425. Min Act: -0.0000

Data Index: 147871 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 6.3667. Min Range: -6.3667

Max Act: 3.4698. Min Act: -0.0000

Data Index: 690405 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 6.3667. Min Range: -6.3667

Max Act: 3.4150. Min Act: -0.0000

Data Index: 431855 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 6.3667. Min Range: -6.3667

Max Act: 3.2554. Min Act: -0.0000

Data Index: 589971 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 6.3667. Min Range: -6.3667

Max Act: 3.5023. Min Act: -0.0000

Data Index: 859117 (C4 (Web Text))

Max Activating Token Index: 8