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

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

Neuron 4796 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2260. Min Act: -0.0002

Data Index: 48599 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2361. Min Act: -0.0002

Data Index: 938257 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2299. Min Act: -0.0002

Data Index: 179168 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2293. Min Act: -0.0002

Data Index: 1160731 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2113. Min Act: -0.0002

Data Index: 1113514 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2270. Min Act: -0.0002

Data Index: 502142 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2181. Min Act: -0.0002

Data Index: 930974 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2161. Min Act: -0.0002

Data Index: 57679 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2110. Min Act: -0.0002

Data Index: 149230 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2164. Min Act: -0.0002

Data Index: 541316 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2089. Min Act: -0.0002

Data Index: 467599 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2217. Min Act: -0.0002

Data Index: 1152278 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2082. Min Act: -0.0002

Data Index: 905783 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2064. Min Act: -0.0002

Data Index: 453397 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1974. Min Act: -0.0002

Data Index: 1176864 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2205. Min Act: -0.0002

Data Index: 1160606 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2052. Min Act: -0.0002

Data Index: 920528 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2047. Min Act: -0.0002

Data Index: 1273142 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2195. Min Act: -0.0002

Data Index: 614593 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2126. Min Act: -0.0002

Data Index: 1152450 (C4 (Web Text))

Max Activating Token Index: 10