Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3069 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.2284. Min Act: -0.0001

Data Index: 824250 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.2011. Min Act: -0.0001

Data Index: 1314551 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1995. Min Act: -0.0001

Data Index: 420022 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.2034. Min Act: -0.0001

Data Index: 1066784 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.2120. Min Act: -0.0001

Data Index: 923267 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.2097. Min Act: -0.0001

Data Index: 736552 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.2001. Min Act: -0.0001

Data Index: 407099 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.2085. Min Act: -0.0001

Data Index: 452850 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.2049. Min Act: -0.0001

Data Index: 664800 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.2041. Min Act: -0.0001

Data Index: 1311276 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.2209. Min Act: -0.0001

Data Index: 494829 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1941. Min Act: -0.0001

Data Index: 1070542 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1897. Min Act: -0.0001

Data Index: 569995 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1996. Min Act: -0.0001

Data Index: 508212 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1999. Min Act: -0.0001

Data Index: 220782 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1759. Min Act: -0.0001

Data Index: 1337196 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.2057. Min Act: -0.0001

Data Index: 128098 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1959. Min Act: -0.0001

Data Index: 85023 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1854. Min Act: -0.0001

Data Index: 123131 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1728. Min Act: -0.0001

Data Index: 759434 (C4 (Web Text))

Max Activating Token Index: 931