Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1067 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.3010. Min Act: -0.0000

Data Index: 461037 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2609. Min Act: -0.0001

Data Index: 373028 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2617. Min Act: -0.0000

Data Index: 867005 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2299. Min Act: -0.0001

Data Index: 111384 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2392. Min Act: -0.0000

Data Index: 726927 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2005. Min Act: -0.0000

Data Index: 962789 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2303. Min Act: -0.0001

Data Index: 622118 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2211. Min Act: -0.0001

Data Index: 88919 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.1995. Min Act: -0.0001

Data Index: 471581 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2216. Min Act: -0.0000

Data Index: 284497 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2142. Min Act: -0.0000

Data Index: 822776 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2081. Min Act: -0.0001

Data Index: 819326 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2000. Min Act: -0.0001

Data Index: 776396 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2190. Min Act: -0.0001

Data Index: 775524 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2134. Min Act: -0.0001

Data Index: 725303 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.1996. Min Act: -0.0000

Data Index: 478527 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2084. Min Act: -0.0000

Data Index: 1342693 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2132. Min Act: -0.0001

Data Index: 1607912 (Python Code)

Max Activating Token Index: 1020

Text #18

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2125. Min Act: -0.0001

Data Index: 1450453 (Python Code)

Max Activating Token Index: 74

Text #19

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.1983. Min Act: -0.0000

Data Index: 1304044 (C4 (Web Text))

Max Activating Token Index: 233