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

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

Neuron 3460 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0195. Min Range: -3.0195

Max Act: 3.0195. Min Act: -0.0000

Data Index: 106174 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 3.0195. Min Range: -3.0195

Max Act: 2.8860. Min Act: -0.0000

Data Index: 1264518 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 3.0195. Min Range: -3.0195

Max Act: 2.2802. Min Act: -0.0000

Data Index: 229561 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 3.0195. Min Range: -3.0195

Max Act: 2.3280. Min Act: -0.0000

Data Index: 667487 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 3.0195. Min Range: -3.0195

Max Act: 2.2992. Min Act: -0.0000

Data Index: 836684 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 3.0195. Min Range: -3.0195

Max Act: 2.2553. Min Act: -0.0000

Data Index: 1190049 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 3.0195. Min Range: -3.0195

Max Act: 2.2267. Min Act: -0.0000

Data Index: 1351250 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 3.0195. Min Range: -3.0195

Max Act: 2.1947. Min Act: -0.0000

Data Index: 446526 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 3.0195. Min Range: -3.0195

Max Act: 2.2013. Min Act: -0.0000

Data Index: 638453 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 3.0195. Min Range: -3.0195

Max Act: 2.2475. Min Act: -0.0000

Data Index: 1162086 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 3.0195. Min Range: -3.0195

Max Act: 2.0056. Min Act: -0.0000

Data Index: 700503 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 3.0195. Min Range: -3.0195

Max Act: 2.1015. Min Act: -0.0000

Data Index: 234633 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 3.0195. Min Range: -3.0195

Max Act: 2.1203. Min Act: -0.0000

Data Index: 1313532 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 3.0195. Min Range: -3.0195

Max Act: 2.1140. Min Act: -0.0000

Data Index: 667866 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 3.0195. Min Range: -3.0195

Max Act: 2.0984. Min Act: -0.0000

Data Index: 231700 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 3.0195. Min Range: -3.0195

Max Act: 2.0875. Min Act: -0.0000

Data Index: 1043395 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 3.0195. Min Range: -3.0195

Max Act: 1.8990. Min Act: -0.0000

Data Index: 405929 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 3.0195. Min Range: -3.0195

Max Act: 1.8220. Min Act: -0.0000

Data Index: 649871 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 3.0195. Min Range: -3.0195

Max Act: 2.0188. Min Act: -0.0000

Data Index: 1331131 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 3.0195. Min Range: -3.0195

Max Act: 2.1214. Min Act: -0.0000

Data Index: 652494 (C4 (Web Text))

Max Activating Token Index: 116