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

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

Neuron 5980 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2478. Min Act: -0.0002

Data Index: 414600 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2377. Min Act: -0.0002

Data Index: 307142 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2284. Min Act: -0.0002

Data Index: 814427 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2282. Min Act: -0.0002

Data Index: 1268075 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2192. Min Act: -0.0002

Data Index: 1296124 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2242. Min Act: -0.0002

Data Index: 598956 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2215. Min Act: -0.0002

Data Index: 871998 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2158. Min Act: -0.0002

Data Index: 1029903 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2155. Min Act: -0.0002

Data Index: 527686 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2152. Min Act: -0.0002

Data Index: 601821 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2173. Min Act: -0.0002

Data Index: 182443 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2139. Min Act: -0.0002

Data Index: 854177 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2085. Min Act: -0.0003

Data Index: 1194043 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2128. Min Act: -0.0002

Data Index: 890163 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2099. Min Act: -0.0002

Data Index: 476777 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2058. Min Act: -0.0002

Data Index: 1316775 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2116. Min Act: -0.0002

Data Index: 685143 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2135. Min Act: -0.0003

Data Index: 1203920 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2126. Min Act: -0.0002

Data Index: 116758 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2146. Min Act: -0.0002

Data Index: 160259 (C4 (Web Text))

Max Activating Token Index: 94