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

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

Neuron 1781 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.2398. Min Act: -0.0001

Data Index: 295 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.4267. Min Act: -0.0000

Data Index: 1091173 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 3.4267. Min Range: -3.4267

Max Act: 2.9908. Min Act: -0.0000

Data Index: 654673 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.1257. Min Act: -0.0000

Data Index: 555230 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 3.4267. Min Range: -3.4267

Max Act: 2.9869. Min Act: -0.0000

Data Index: 566336 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 3.4267. Min Range: -3.4267

Max Act: 2.8932. Min Act: -0.0001

Data Index: 500215 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.1662. Min Act: -0.0000

Data Index: 1349009 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 3.4267. Min Range: -3.4267

Max Act: 2.7330. Min Act: -0.0000

Data Index: 125145 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 3.4267. Min Range: -3.4267

Max Act: 2.8093. Min Act: -0.0000

Data Index: 1178959 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 3.4267. Min Range: -3.4267

Max Act: 2.8210. Min Act: -0.0000

Data Index: 1194284 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 3.4267. Min Range: -3.4267

Max Act: 2.5574. Min Act: -0.0000

Data Index: 1245531 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 3.4267. Min Range: -3.4267

Max Act: 2.7616. Min Act: -0.0001

Data Index: 1159418 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 3.4267. Min Range: -3.4267

Max Act: 2.5087. Min Act: -0.0001

Data Index: 663037 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 3.4267. Min Range: -3.4267

Max Act: 2.5869. Min Act: -0.0001

Data Index: 653463 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 3.4267. Min Range: -3.4267

Max Act: 2.5679. Min Act: -0.0000

Data Index: 269224 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 3.4267. Min Range: -3.4267

Max Act: 2.4453. Min Act: -0.0001

Data Index: 724795 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 3.4267. Min Range: -3.4267

Max Act: 2.5754. Min Act: -0.0000

Data Index: 187214 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 3.4267. Min Range: -3.4267

Max Act: 2.5129. Min Act: -0.0001

Data Index: 207701 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 3.4267. Min Range: -3.4267

Max Act: 2.5711. Min Act: -0.0000

Data Index: 1297548 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 3.4267. Min Range: -3.4267

Max Act: 2.5385. Min Act: -0.0001

Data Index: 457062 (C4 (Web Text))

Max Activating Token Index: 213