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

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

Neuron 3570 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8112. Min Range: -2.8112

Max Act: 2.7278. Min Act: -0.0000

Data Index: 804707 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 2.8112. Min Range: -2.8112

Max Act: 2.7413. Min Act: -0.0000

Data Index: 67122 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 2.8112. Min Range: -2.8112

Max Act: 2.8112. Min Act: -0.0000

Data Index: 589254 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 2.8112. Min Range: -2.8112

Max Act: 2.6648. Min Act: -0.0000

Data Index: 75172 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 2.8112. Min Range: -2.8112

Max Act: 2.5860. Min Act: -0.0000

Data Index: 736083 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 2.8112. Min Range: -2.8112

Max Act: 2.7229. Min Act: -0.0000

Data Index: 755509 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 2.8112. Min Range: -2.8112

Max Act: 2.4127. Min Act: -0.0000

Data Index: 33229 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 2.8112. Min Range: -2.8112

Max Act: 2.4389. Min Act: -0.0000

Data Index: 664461 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 2.8112. Min Range: -2.8112

Max Act: 2.3907. Min Act: -0.0000

Data Index: 1151288 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 2.8112. Min Range: -2.8112

Max Act: 2.4010. Min Act: -0.0000

Data Index: 524863 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 2.8112. Min Range: -2.8112

Max Act: 2.2328. Min Act: -0.0000

Data Index: 671881 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 2.8112. Min Range: -2.8112

Max Act: 2.2361. Min Act: -0.0000

Data Index: 2632 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 2.8112. Min Range: -2.8112

Max Act: 2.2234. Min Act: -0.0000

Data Index: 293962 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 2.8112. Min Range: -2.8112

Max Act: 2.3285. Min Act: -0.0000

Data Index: 525521 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 2.8112. Min Range: -2.8112

Max Act: 2.1722. Min Act: -0.0000

Data Index: 1029010 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 2.8112. Min Range: -2.8112

Max Act: 2.2917. Min Act: -0.0000

Data Index: 832633 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 2.8112. Min Range: -2.8112

Max Act: 1.9045. Min Act: -0.0000

Data Index: 653708 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 2.8112. Min Range: -2.8112

Max Act: 1.9379. Min Act: -0.0000

Data Index: 397803 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 2.8112. Min Range: -2.8112

Max Act: 2.3060. Min Act: -0.0000

Data Index: 365655 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 2.8112. Min Range: -2.8112

Max Act: 2.1660. Min Act: -0.0000

Data Index: 395142 (C4 (Web Text))

Max Activating Token Index: 9