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

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

Neuron 5761 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1646. Min Act: -0.0000

Data Index: 1307870 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1438. Min Act: -0.0000

Data Index: 484272 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1227. Min Act: -0.0000

Data Index: 134455 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1301. Min Act: -0.0000

Data Index: 235274 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1199. Min Act: -0.0000

Data Index: 50519 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1197. Min Act: -0.0000

Data Index: 708961 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1122. Min Act: -0.0000

Data Index: 565598 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1251. Min Act: -0.0000

Data Index: 629563 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1135. Min Act: -0.0000

Data Index: 148959 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1167. Min Act: -0.0000

Data Index: 407196 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1154. Min Act: -0.0000

Data Index: 796176 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1153. Min Act: -0.0000

Data Index: 504755 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1100. Min Act: -0.0000

Data Index: 161284 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1046. Min Act: -0.0000

Data Index: 628178 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1047. Min Act: -0.0000

Data Index: 882268 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1310208 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1126264 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1045. Min Act: -0.0000

Data Index: 738927 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1006. Min Act: -0.0000

Data Index: 1270755 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1042. Min Act: -0.0000

Data Index: 519347 (C4 (Web Text))

Max Activating Token Index: 65