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

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

Neuron 12 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7850. Min Range: -2.7850

Max Act: 2.7850. Min Act: -0.0000

Data Index: 1112733 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.5555. Min Act: -0.0000

Data Index: 872270 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.6234. Min Act: -0.0000

Data Index: 1133154 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.4148. Min Act: -0.0000

Data Index: 1256147 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.3373. Min Act: -0.0000

Data Index: 788327 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 2.7850. Min Range: -2.7850

Max Act: 1.0008. Min Act: -0.0000

Data Index: 801692 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 2.7850. Min Range: -2.7850

Max Act: 0.9514. Min Act: -0.0000

Data Index: 632889 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 2.7850. Min Range: -2.7850

Max Act: 0.9025. Min Act: -0.0000

Data Index: 864764 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 2.7850. Min Range: -2.7850

Max Act: 0.9247. Min Act: -0.0000

Data Index: 1225888 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 2.7850. Min Range: -2.7850

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1028499 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 2.7850. Min Range: -2.7850

Max Act: 0.8865. Min Act: -0.0000

Data Index: 813533 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 2.7850. Min Range: -2.7850

Max Act: 0.8819. Min Act: -0.0000

Data Index: 926740 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 2.7850. Min Range: -2.7850

Max Act: 0.8372. Min Act: -0.0000

Data Index: 1170364 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 2.7850. Min Range: -2.7850

Max Act: 0.8379. Min Act: -0.0000

Data Index: 448031 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 2.7850. Min Range: -2.7850

Max Act: 0.7923. Min Act: -0.0000

Data Index: 218382 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 2.7850. Min Range: -2.7850

Max Act: 0.7740. Min Act: -0.0000

Data Index: 288326 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 2.7850. Min Range: -2.7850

Max Act: 0.8106. Min Act: -0.0000

Data Index: 265579 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 2.7850. Min Range: -2.7850

Max Act: 0.7524. Min Act: -0.0000

Data Index: 1345818 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 2.7850. Min Range: -2.7850

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1289517 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 2.7850. Min Range: -2.7850

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1228422 (C4 (Web Text))

Max Activating Token Index: 941