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

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

Neuron 4839 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8166. Min Range: -6.8166

Max Act: 6.8166. Min Act: -0.0000

Data Index: 143202 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 6.8166. Min Range: -6.8166

Max Act: 5.0869. Min Act: -0.0000

Data Index: 1225001 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 6.8166. Min Range: -6.8166

Max Act: 5.7921. Min Act: -0.0000

Data Index: 151709 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 6.8166. Min Range: -6.8166

Max Act: 5.6427. Min Act: -0.0000

Data Index: 1165564 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 6.8166. Min Range: -6.8166

Max Act: 5.0809. Min Act: -0.0000

Data Index: 721591 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 6.8166. Min Range: -6.8166

Max Act: 5.5357. Min Act: -0.0000

Data Index: 1158103 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 6.8166. Min Range: -6.8166

Max Act: 5.1601. Min Act: -0.0000

Data Index: 408220 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 6.8166. Min Range: -6.8166

Max Act: 4.9765. Min Act: -0.0000

Data Index: 36306 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 6.8166. Min Range: -6.8166

Max Act: 5.6097. Min Act: -0.0000

Data Index: 953352 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 6.8166. Min Range: -6.8166

Max Act: 4.9964. Min Act: -0.0000

Data Index: 584578 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 6.8166. Min Range: -6.8166

Max Act: 5.3736. Min Act: -0.0000

Data Index: 103122 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 6.8166. Min Range: -6.8166

Max Act: 5.2290. Min Act: -0.0000

Data Index: 195937 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 6.8166. Min Range: -6.8166

Max Act: 3.9731. Min Act: -0.0000

Data Index: 285868 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 6.8166. Min Range: -6.8166

Max Act: 5.1849. Min Act: -0.0000

Data Index: 935272 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 6.8166. Min Range: -6.8166

Max Act: 4.2432. Min Act: -0.0000

Data Index: 1068441 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 6.8166. Min Range: -6.8166

Max Act: 3.7080. Min Act: -0.0000

Data Index: 276907 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 6.8166. Min Range: -6.8166

Max Act: 4.0568. Min Act: -0.0000

Data Index: 1152192 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 6.8166. Min Range: -6.8166

Max Act: 3.8966. Min Act: -0.0000

Data Index: 694768 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 6.8166. Min Range: -6.8166

Max Act: 3.4333. Min Act: -0.0000

Data Index: 1085054 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 6.8166. Min Range: -6.8166

Max Act: 3.7304. Min Act: -0.0000

Data Index: 902161 (C4 (Web Text))

Max Activating Token Index: 320