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

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

Neuron 1742 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: 3.0919. Min Range: -3.0919

Max Act: 3.0810. Min Act: -0.0000

Data Index: 1421010 (Python Code)

Max Activating Token Index: 853

Text #1

Max Range: 3.0919. Min Range: -3.0919

Max Act: 3.0919. Min Act: -0.0000

Data Index: 1482329 (Python Code)

Max Activating Token Index: 631

Text #2

Max Range: 3.0919. Min Range: -3.0919

Max Act: 3.0552. Min Act: -0.0000

Data Index: 1577980 (Python Code)

Max Activating Token Index: 366

Text #3

Max Range: 3.0919. Min Range: -3.0919

Max Act: 2.9232. Min Act: -0.0000

Data Index: 1608795 (Python Code)

Max Activating Token Index: 788

Text #4

Max Range: 3.0919. Min Range: -3.0919

Max Act: 3.0528. Min Act: -0.0000

Data Index: 1491362 (Python Code)

Max Activating Token Index: 194

Text #5

Max Range: 3.0919. Min Range: -3.0919

Max Act: 2.0150. Min Act: -0.0000

Data Index: 1224037 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 3.0919. Min Range: -3.0919

Max Act: 1.9760. Min Act: -0.0000

Data Index: 1144124 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 3.0919. Min Range: -3.0919

Max Act: 1.6030. Min Act: -0.0000

Data Index: 439260 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 3.0919. Min Range: -3.0919

Max Act: 1.5248. Min Act: -0.0000

Data Index: 84791 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 3.0919. Min Range: -3.0919

Max Act: 1.6157. Min Act: 0.0000

Data Index: 1057423 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 3.0919. Min Range: -3.0919

Max Act: 1.5101. Min Act: -0.0000

Data Index: 1418598 (Python Code)

Max Activating Token Index: 532

Text #11

Max Range: 3.0919. Min Range: -3.0919

Max Act: 1.5129. Min Act: 0.0000

Data Index: 690443 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 3.0919. Min Range: -3.0919

Max Act: 1.3966. Min Act: -0.0000

Data Index: 869890 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 3.0919. Min Range: -3.0919

Max Act: 1.4938. Min Act: -0.0000

Data Index: 669319 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 3.0919. Min Range: -3.0919

Max Act: 1.4802. Min Act: -0.0000

Data Index: 697033 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 3.0919. Min Range: -3.0919

Max Act: 1.3000. Min Act: -0.0000

Data Index: 788752 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 3.0919. Min Range: -3.0919

Max Act: 1.4515. Min Act: -0.0000

Data Index: 320638 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 3.0919. Min Range: -3.0919

Max Act: 1.4740. Min Act: -0.0000

Data Index: 1505070 (Python Code)

Max Activating Token Index: 707

Text #18

Max Range: 3.0919. Min Range: -3.0919

Max Act: 1.4336. Min Act: -0.0000

Data Index: 429302 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 3.0919. Min Range: -3.0919

Max Act: 1.4102. Min Act: -0.0000

Data Index: 353930 (C4 (Web Text))

Max Activating Token Index: 825