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

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

Neuron 3073 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.4182. Min Act: -0.0000

Data Index: 853797 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1261745 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3469. Min Act: -0.0000

Data Index: 588284 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3337. Min Act: -0.0000

Data Index: 252276 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3385. Min Act: -0.0000

Data Index: 621099 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3364. Min Act: -0.0000

Data Index: 825356 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3283. Min Act: -0.0000

Data Index: 748824 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3222. Min Act: -0.0000

Data Index: 297361 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3208. Min Act: -0.0000

Data Index: 10542 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3387. Min Act: -0.0000

Data Index: 1319678 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1320838 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3134. Min Act: -0.0000

Data Index: 225827 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2931. Min Act: -0.0000

Data Index: 775775 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2853. Min Act: -0.0000

Data Index: 343435 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3046. Min Act: -0.0000

Data Index: 980492 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3033. Min Act: -0.0000

Data Index: 997236 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2796. Min Act: -0.0000

Data Index: 364160 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2757. Min Act: -0.0000

Data Index: 275444 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2625. Min Act: -0.0000

Data Index: 812938 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2746. Min Act: -0.0000

Data Index: 424091 (C4 (Web Text))

Max Activating Token Index: 378