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

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

Neuron 1344 in Layer 0

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: 0.0212. Min Range: -0.0212

Max Act: 0.0212. Min Act: -0.0001

Data Index: 604862 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0208. Min Act: -0.0001

Data Index: 1640868 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0194. Min Act: -0.0002

Data Index: 1553622 (Python Code)

Max Activating Token Index: 122

Text #3

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0191. Min Act: -0.0001

Data Index: 1590063 (Python Code)

Max Activating Token Index: 671

Text #4

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0184. Min Act: -0.0001

Data Index: 1166070 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0185. Min Act: -0.0001

Data Index: 1466055 (Python Code)

Max Activating Token Index: 125

Text #6

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1486878 (Python Code)

Max Activating Token Index: 252

Text #7

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0183. Min Act: -0.0001

Data Index: 1246477 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0174. Min Act: -0.0001

Data Index: 212351 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1547991 (Python Code)

Max Activating Token Index: 951

Text #10

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0175. Min Act: -0.0001

Data Index: 363097 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1406554 (Python Code)

Max Activating Token Index: 155

Text #12

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1487174 (Python Code)

Max Activating Token Index: 838

Text #13

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0168. Min Act: -0.0001

Data Index: 1461665 (Python Code)

Max Activating Token Index: 366

Text #14

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1289656 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1485244 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0172. Min Act: -0.0001

Data Index: 763252 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1504500 (Python Code)

Max Activating Token Index: 712

Text #18

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0169. Min Act: -0.0001

Data Index: 778690 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0168. Min Act: -0.0001

Data Index: 1551175 (Python Code)

Max Activating Token Index: 106