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

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

Neuron 5248 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: 2.1981. Min Range: -2.1981

Max Act: 2.1981. Min Act: -0.0000

Data Index: 654728 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 2.1981. Min Range: -2.1981

Max Act: 1.8214. Min Act: -0.0000

Data Index: 194719 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 2.1981. Min Range: -2.1981

Max Act: 1.7697. Min Act: -0.0000

Data Index: 802130 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 2.1981. Min Range: -2.1981

Max Act: 1.6609. Min Act: -0.0000

Data Index: 1276468 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 2.1981. Min Range: -2.1981

Max Act: 1.6457. Min Act: -0.0000

Data Index: 779465 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 2.1981. Min Range: -2.1981

Max Act: 1.5244. Min Act: -0.0000

Data Index: 1130026 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 2.1981. Min Range: -2.1981

Max Act: 1.6140. Min Act: -0.0000

Data Index: 1206102 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 2.1981. Min Range: -2.1981

Max Act: 1.6033. Min Act: -0.0000

Data Index: 844380 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 2.1981. Min Range: -2.1981

Max Act: 1.4662. Min Act: -0.0000

Data Index: 464769 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 2.1981. Min Range: -2.1981

Max Act: 1.5292. Min Act: -0.0000

Data Index: 367787 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 2.1981. Min Range: -2.1981

Max Act: 1.4982. Min Act: -0.0000

Data Index: 718655 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 2.1981. Min Range: -2.1981

Max Act: 1.4790. Min Act: -0.0000

Data Index: 942486 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 2.1981. Min Range: -2.1981

Max Act: 1.4722. Min Act: -0.0000

Data Index: 164527 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 2.1981. Min Range: -2.1981

Max Act: 1.4642. Min Act: -0.0000

Data Index: 326310 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 2.1981. Min Range: -2.1981

Max Act: 1.4481. Min Act: -0.0000

Data Index: 410382 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 2.1981. Min Range: -2.1981

Max Act: 1.4551. Min Act: -0.0000

Data Index: 405776 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 2.1981. Min Range: -2.1981

Max Act: 1.4256. Min Act: -0.0000

Data Index: 101756 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 2.1981. Min Range: -2.1981

Max Act: 1.4191. Min Act: -0.0000

Data Index: 1266615 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 2.1981. Min Range: -2.1981

Max Act: 1.4090. Min Act: -0.0000

Data Index: 616971 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 2.1981. Min Range: -2.1981

Max Act: 1.3838. Min Act: -0.0000

Data Index: 270576 (C4 (Web Text))

Max Activating Token Index: 875